© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4924
    Prev
    Next
    INDEX
    Explanations

    LaTeX math notation

    oai_token-act-pair · gemini-2.0-flash

    equations and formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     tadi
    -0.44
     lumineuse
    -0.40
     égale
    -0.39
    Non
    -0.38
     intérieure
    -0.37
    migrationBuilder
    -0.37
    유
    -0.36
     Integration
    -0.36
     risultato
    -0.35
     surprised
    -0.35
    POSITIVE LOGITS
    ThroughAttribute
    0.89
    Personensuche
    0.86
    parsedMessage
    0.86
    存于互联网档案馆
    0.84
     resourceCulture
    0.84
    LookAnd
    0.84
     المعيارى
    0.84
     Lightboxes
    0.77
     Normdatei
    0.74
    principalTable
    0.74
    Activations Density 15.668%

    No Known Activations