© 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. 2800
    Prev
    Next
    INDEX
    Explanations

    the end of statements

    oai_token-act-pair · gemini-2.0-flash

    ellipses

    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
    Identyfik
    -0.57
    +#+
    -0.57
    Билгалдахарш
    -0.55
    Hentet
    -0.52
    出版年
    -0.50
    rrggbb
    -0.50
    PerformLayout
    -0.47
     Coro
    -0.46
     autorytatywna
    -0.46
    Rüyada
    -0.45
    POSITIVE LOGITS
    ️
    0.57
    بوابة
    0.54
    makeConstraints
    0.52
     spørsmål
    0.51
    (',')
    0.50
    انتهای
    0.50
    yntaxException
    0.50
     Schenk
    0.50
    🏻‍♀️
    0.50
    hdessä
    0.50
    Activations Density 3.743%

    No Known Activations