© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2259
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to death, violence, and the legal system.

    oai_token-act-pair · gemini-2.0-flash

    related people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     referenties
    -0.56
     Paglinawan
    -0.53
    Jeografia
    -0.48
    MLLoader
    -0.48
     déploy
    -0.46
    igent
    -0.46
    onauts
    -0.46
    iconque
    -0.45
    effort
    -0.45
     installation
    -0.44
    POSITIVE LOGITS
     bağlantılar
    0.63
     contextLoads
    0.63
    BagConstraints
    0.58
    Revenir
    0.56
     <=",
    0.56
    +#+#
    0.54
    OOTDTY
    0.54
     Stapleton
    0.54
    lepiej
    0.54
     Commencez
    0.54
    Activations Density 26.130%

    No Known Activations