© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10200
    Prev
    Next
    INDEX
    Explanations

    very long numbers

    oai_token-act-pair · gemini-2.0-flash

    Code and identifiers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Avez
    -0.38
     rang
    -0.36
     مشارکت‌کنندگان
    -0.35
    WindowConstants
    -0.34
    fords
    -0.34
     ostavi
    -0.34
    cy
    -0.33
    난
    -0.33
    rån
    -0.33
    ford
    -0.33
    POSITIVE LOGITS
    BagLayout
    0.69
    ьаж
    0.64
    saraba
    0.63
     Molo
    0.63
    esModule
    0.62
    tvguidetime
    0.62
     saiba
    0.61
    
    0.61
    ynchronously
    0.60
    neſs
    0.60
    Activations Density 0.371%

    No Known Activations