© 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. 1161
    Prev
    Next
    INDEX
    Explanations

    content-free tokens representing math and programming syntax like variable names, labels, and numbers

    oai_token-act-pair · gemini-2.0-flash

    finance/money

    np_max-act · 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
     оригіналу
    -0.48
    selectAll
    -0.44
    מוש
    -0.43
     onOptions
    -0.41
     aid
    -0.40
     ad
    -0.39
    fels
    -0.39
    TableId
    -0.39
     XCTest
    -0.39
    char
    -0.39
    POSITIVE LOGITS
     تضيفلها
    0.77
    Lähteet
    0.72
    saraba
    0.69
     ostavi
    0.68
     الحره
    0.66
    PerformLayout
    0.66
    Personendaten
    0.64
     مشين
    0.64
    WindowConstants
    0.62
     Alembic
    0.60
    Activations Density 2.496%

    No Known Activations