© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16223
    Prev
    Next
    INDEX
    Explanations

    code snippets in multiple languages and foreign words

    oai_token-act-pair · gemini-2.0-flash

    non-English text

    np_max-act · gemini-2.0-flash

    say "▁" Method used: 2 — Tokens mostly start with "▁"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.89
     geslacht
    -0.76
     فريبيس
    -0.72
     Biôgrafia
    -0.71
     виправивши
    -0.64
     gawas
    -0.63
     chi̍t
    -0.62
    లాలు
    -0.60
     today
    -0.60
     ویکی‌پدیای
    -0.60
    POSITIVE LOGITS
    <bos>
    0.87
    OrBuilder
    0.58
    ⓧ
    0.55
    #
    0.52
     spit
    0.51
    tubers
    0.47
     niger
    0.47
     onAnimation
    0.46
    rotnie
    0.46
     getItemId
    0.45
    Activations Density 2.609%

    No Known Activations