© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10324
    Prev
    Next
    INDEX
    Explanations

    information, particularly historical information, about science fiction

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    App
    -0.36
     o
    -0.35
     App
    -0.33
    ophage
    -0.30
    app
    -0.30
     montré
    -0.29
    vyšší
    -0.29
     considere
    -0.29
    муж
    -0.29
     R
    -0.28
    POSITIVE LOGITS
    IsContent
    1.09
     &___
    1.05
    出版年
    1.01
    JspWriter
    0.98
     مشين
    0.96
    ]--;
    0.95
    +#+
    0.95
    RectangleBorder
    0.94
    protoc
    0.93
    GraphicsUnit
    0.93
    Activations Density 24.380%

    No Known Activations