© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10559
    Prev
    Next
    INDEX
    Explanations

    questions asking for help and suggestions

    oai_token-act-pair · gemini-2.0-flash

    requests for suggestions/ideas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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>
    -0.60
    Otras
    -0.42
    κλη
    -0.41
     turned
    -0.40
     How
    -0.40
    uxxxx
    -0.39
    $?
    -0.39
    v
    -0.38
     responded
    -0.38
    jegy
    -0.38
    POSITIVE LOGITS
    CloseOperation
    0.79
    findpost
    0.79
    featureID
    0.73
    rungsseite
    0.72
    parsedMessage
    0.68
    脚注の使い方
    0.67
    ゴリー
    0.66
    Personensuche
    0.66
    ThroughAttribute
    0.65
    principalColumn
    0.63
    Activations Density 0.197%

    No Known Activations