© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10776
    Prev
    Next
    INDEX
    Explanations

    scientific or mathematical articles, including numbers in parenthesis or percentages

    oai_token-act-pair · gemini-2.0-flash

    Parenthesis and Dashes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     ionized
    -0.38
     $
    -0.37
     electrolytes
    -0.36
     PRESENTED
    -0.35
     inducted
    -0.35
     initiated
    -0.34
     linearized
    -0.33
     narrated
    -0.33
     sulphide
    -0.33
     concluded
    -0.32
    POSITIVE LOGITS
    例文帳に追加
    0.77
     ModelExpression
    0.75
    MigrationBuilder
    0.73
    forName
    0.69
    fromCharCode
    0.67
    UAE
    0.67
    ➟
    0.66
    Forty
    0.66
     الحره
    0.65
    Personendaten
    0.65
    Activations Density 20.320%

    No Known Activations