© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14040
    Prev
    Next
    INDEX
    Explanations

    tokens in scientific papers corresponding to components of figures, plots, and graphs

    oai_token-act-pair · gemini-2.0-flash

    Panel or line

    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
    rungsseite
    -0.63
    KURZBESCHREIBUNG
    -0.60
     himo
    -0.55
    mybatisplus
    -0.54
    ngdoc
    -0.54
    LookAnd
    -0.53
    :✨
    -0.53
    PreferredItem
    -0.52
    errHandler
    -0.52
     disambiguazione
    -0.52
    POSITIVE LOGITS
    <bos>
    1.05
     mẽ
    0.57
     تانيه
    0.57
    struktion
    0.56
     devriez
    0.54
     récentes
    0.54
    therosclerosis
    0.54
     musée
    0.53
     angekommen
    0.51
    isNameExpr
    0.50
    Activations Density 3.452%

    No Known Activations