© 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. 4875
    Prev
    Next
    INDEX
    Explanations

    statements where people express how they feel about things

    oai_token-act-pair · gemini-2.0-flash

    Justifications for actions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Obrázky
    -0.90
    ScopeManager
    -0.86
     resourceCulture
    -0.82
    +#+#
    -0.81
    migrationBuilder
    -0.79
    Revenir
    -0.78
    RenderAtEndOf
    -0.77
     Bioaccumulative
    -0.75
     Taktlose
    -0.75
     MotionEvent
    -0.74
    POSITIVE LOGITS
     referenties
    0.44
    անում
    0.38
    وام
    0.36
     Press
    0.35
     referencias
    0.35
     جذ
    0.35
    Overview
    0.34
     S
    0.33
    дравству
    0.32
    itamente
    0.32
    Activations Density 2.760%

    No Known Activations