© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8271
    Prev
    Next
    INDEX
    Explanations

    personal associations between people, locations, and items

    oai_token-act-pair · gemini-2.0-flash

    in

    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
    Negative Logits
     שוליים
    -0.54
     متعلقه
    -0.49
    Composable
    -0.47
     anytime
    -0.43
     Celui
    -0.43
    StoryboardSegue
    -0.43
    CellStyle
    -0.40
    梅
    -0.40
     Bolívar
    -0.40
    Eligibility
    -0.40
    POSITIVE LOGITS
    ftagPool
    0.75
    adpleegd
    0.75
    IUrlHelper
    0.73
    niczka
    0.72
    MigrationBuilder
    0.70
     Réponses
    0.69
    StructEnd
    0.68
    oredCriteria
    0.67
    脚注の使い方
    0.66
     ويكيپيديا
    0.66
    Activations Density 1.454%

    No Known Activations