© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4177
    Prev
    Next
    INDEX
    Explanations

    colons, titles and the words "from", "theory", "evaluation", "and" and "containing"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -0.84
     cherchés
    -0.57
     Infórmanos
    -0.51
    PositiveButton
    -0.46
     Credential
    -0.45
     attaque
    -0.45
    RenderAtEndOf
    -0.44
    kháu
    -0.43
     <>",
    -0.43
    nsis
    -0.42
    POSITIVE LOGITS
    classnames
    0.77
    ⓧ
    0.58
    AccessorTable
    0.58
     lenker
    0.56
    ulse
    0.56
     RISERV
    0.56
    IsContent
    0.54
    참고
    0.54
     torchvision
    0.53
    aksikan
    0.53
    Activations Density 12.888%

    No Known Activations