© 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
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 11887
    Prev
    Next
    INDEX
    Explanations

    descriptions of coatings, finishes, and materials

    oai_token-act-pair · gemini-2.0-flash

    Surface coatings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    っこう
    -0.50
     historial
    -0.48
    UnknownFieldSet
    -0.46
    anskrit
    -0.46
    erschrank
    -0.45
    ческа
    -0.44
    PageRoute
    -0.44
     GeoNames
    -0.42
     luy
    -0.42
    nbsp
    -0.42
    POSITIVE LOGITS
    UnusedPrivate
    0.68
     Majefty
    0.66
    <bos>
    0.64
     Monfieur
    0.64
     Jefus
    0.62
     myſelf
    0.61
    migrationBuilder
    0.60
    numerusform
    0.59
     مشارکت‌کنندگان
    0.56
    tagHelperRunner
    0.56
    Activations Density 0.579%

    No Known Activations