© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11122
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with the process of disseminating information to a wide audience, including distribution of materials and promotion of events and ideas, as well as actions, events, and other words related to printed materials.

    oai_token-act-pair · gemini-2.0-flash

    distribute

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     distribution
    -1.52
     Distribution
    -1.34
     distributing
    -1.31
     distribute
    -1.29
     distributions
    -1.27
     distributes
    -1.27
    distribution
    -1.26
    Distribution
    -1.25
     distribuição
    -1.21
     distributed
    -1.19
    POSITIVE LOGITS
    rahmen
    0.57
     seniority
    0.56
    XmlAccessorType
    0.51
     crucible
    0.50
     calldata
    0.49
    Mutagenicity
    0.49
     hangers
    0.48
     hanger
    0.48
    jdk
    0.47
    üksek
    0.46
    Activations Density 28.985%

    No Known Activations