© 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. 2815
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands for tables and arrays

    oai_token-act-pair · gemini-2.0-flash

    code and math snippets

    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
     itſelf
    -0.96
     myſelf
    -0.93
     Theſe
    -0.93
     Anſ
    -0.90
     Reſ
    -0.90
     leſs
    -0.88
     ſmall
    -0.85
     ſeveral
    -0.85
    ſelf
    -0.84
     leaſt
    -0.84
    POSITIVE LOGITS
    |
    0.54
    —
    0.53
     
    0.48
     —
    0.48
     csoport
    0.45
    etragen
    0.42
     Gelegenheit
    0.41
    ेंद्र
    0.41
     социальной
    0.41
     ad
    0.40
    Activations Density 0.160%

    No Known Activations