© 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. 11798
    Prev
    Next
    INDEX
    Explanations

    times and days

    oai_token-act-pair · gemini-2.0-flash

    3

    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
    tainer
    -0.48
    Hauptartikel
    -0.48
     مشارکت‌کنندگان
    -0.47
    ujudkan
    -0.47
     lebar
    -0.46
     löytyy
    -0.45
     Lehre
    -0.45
     stationnement
    -0.44
    OrDefault
    -0.44
     Vorsitzende
    -0.44
    POSITIVE LOGITS
    IndentedString
    0.72
    ArrowToggle
    0.70
    MigrationBuilder
    0.69
     ProtoMessage
    0.69
    EndContext
    0.67
     nakalista
    0.67
    IntoConstraints
    0.66
    InjectAttribute
    0.62
    RectangleBorder
    0.59
    localctx
    0.58
    Activations Density 0.685%

    No Known Activations