Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 7-GEMMASCOPE-TRANSCODER-16K
    4. 6797
    Prev
    Next
    INDEX
    Explanations

    LaTeX code for displaying tables, arrays, and formulas

    oai_token-act-pair · gemini-2.0-flash

    arrays and tables

    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
    tabular
    -0.65
     Her
    -0.39
    ulemon
    -0.39
    ילות
    -0.39
     we
    -0.39
    juna
    -0.38
    akuza
    -0.37
    OTTEN
    -0.37
    apunov
    -0.36
    aughey
    -0.36
    POSITIVE LOGITS
    TagMode
    1.04
    endphp
    0.84
    setVerticalGroup
    0.83
    WebElementEntity
    0.75
     Мексичка
    0.73
    DeleteBehavior
    0.71
    Билгалдахарш
    0.71
    initializeApp
    0.68
    principalColumn
    0.66
    MigrationBuilder
    0.66
    Activations Density 0.435%

    No Known Activations