© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12904
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to law, mathematics, scientific principles, and political systems, particularly where abstract concepts are being discussed.

    oai_token-act-pair · gemini-2.0-flash

    math and logic

    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
     Signalez
    -0.81
     unknownFields
    -0.73
    tagHelperRunner
    -0.73
     ModelExpression
    -0.69
     autorytatywna
    -0.68
     allAfrica
    -0.65
     GetEnumerator
    -0.61
     дописавши
    -0.60
    migrationBuilder
    -0.59
     فريبيس
    -0.59
    POSITIVE LOGITS
    mybatisplus
    0.53
    esModule
    0.52
    脚注の使い方
    0.48
    requestCode
    0.45
     peix
    0.44
    EndContext
    0.43
    withIdentifier
    0.42
    lorette
    0.42
     insuffisamment
    0.41
    inquirer
    0.41
    Activations Density 3.326%

    No Known Activations