© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7193
    Prev
    Next
    INDEX
    Explanations

    words generally related to vehicles or cars, and more specifically golf carts

    oai_token-act-pair · gemini-2.0-flash

    Car brands and foreign text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    httphttps
    -0.50
     combineReducers
    -0.49
     tax
    -0.47
    ırı
    -0.47
     Tax
    -0.45
    lax
    -0.45
     Interference
    -0.44
     Sequelize
    -0.44
     recensement
    -0.44
    TAX
    -0.44
    POSITIVE LOGITS
     Monfieur
    0.73
     Eſ
    0.68
     Jefus
    0.67
    Viki
    0.66
    tvguidetime
    0.66
     avoit
    0.65
     juſ
    0.65
     ſche
    0.63
     Efq
    0.63
     itſelf
    0.62
    Activations Density 0.847%

    No Known Activations