© 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. 10186
    Prev
    Next
    INDEX
    Explanations

    words related to commercial products, inventions, and chemical elements

    oai_token-act-pair · gemini-2.0-flash

    business and bowling

    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
     nahilalakip
    -0.72
     مشين
    -0.71
    schild
    -0.68
     BoxFit
    -0.63
    日閲覧
    -0.62
    Solución
    -0.61
    wapV
    -0.60
    RenderAtEndOf
    -0.60
    참고
    -0.59
     isNameExpr
    -0.56
    POSITIVE LOGITS
     Ogle
    0.51
    Xaml
    0.51
     endom
    0.50
     escuchado
    0.50
     ſte
    0.49
     privées
    0.49
     ovale
    0.48
     Gentleman
    0.47
     wezen
    0.47
    Leaders
    0.47
    Activations Density 3.919%

    No Known Activations