© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10887
    Prev
    Next
    INDEX
    Explanations

    words related to wine

    oai_token-act-pair · gemini-2.0-flash

    wine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     fédé
    -0.75
     figliu
    -0.75
     enfans
    -0.73
     Púb
    -0.73
    ValueStyle
    -0.71
    bootstrapcdn
    -0.70
     chré
    -0.69
     ब्रेकडाउन
    -0.69
     autorité
    -0.66
    ddots
    -0.66
    POSITIVE LOGITS
    ↵↵
    0.74
    ↵
    0.62
    '
    0.58
    RenderAtEndOf
    0.56
    lgari
    0.55
    roir
    0.52
    inol
    0.47
     law
    0.47
    OkHttpClient
    0.46
    <bos>
    0.45
    Activations Density 1.346%

    No Known Activations