© 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. 4245
    Prev
    Next
    INDEX
    Explanations

    words that intensify or modify a statement, or indicate a point in a series of events (e.g. "literally," "even," "already").

    oai_token-act-pair · gemini-2.0-flash

    literally

    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
     AssemblyCulture
    -0.61
    ReusableCell
    -0.55
     JAXBElement
    -0.55
     متعلقه
    -0.52
     resourceCulture
    -0.52
    FieldNumber
    -0.50
     Roskov
    -0.50
    Gambas
    -0.49
    WireFormatLite
    -0.48
    enoid
    -0.48
    POSITIVE LOGITS
    <bos>
    0.84
     nakalista
    0.73
     autorytatywna
    0.64
    devamını
    0.58
    apimachinery
    0.57
    Geplaatst
    0.56
    Дереккөздер
    0.56
     addirittura
    0.54
     halbe
    0.54
     dozen
    0.54
    Activations Density 2.247%

    No Known Activations