© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11779
    Prev
    Next
    INDEX
    Explanations

    text about funding, especially for public education.

    oai_token-act-pair · gemini-2.0-flash

    distribute

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ValueStyle
    -0.59
     &___
    -0.56
     autorytatywna
    -0.52
    Démographie
    -0.46
    DockStyle
    -0.46
     fund
    -0.45
     co
    -0.45
     funding
    -0.44
     financi
    -0.43
     Administrativna
    -0.42
    POSITIVE LOGITS
     distribute
    0.79
     Distribute
    0.79
     distribution
    0.77
     DISTRIBUTION
    0.75
     distributions
    0.73
    DISTRIBUTION
    0.73
     distributes
    0.73
     Distributions
    0.73
     distributing
    0.72
    distributions
    0.71
    Activations Density 1.719%

    No Known Activations