© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14582
    Prev
    Next
    INDEX
    Explanations

    sentences starting with transition words or parenthetical comma-separated thoughts.

    oai_token-act-pair · gemini-2.0-flash

    non-English words or phrases

    np_token-act-pair-logits · gpt-4o-mini

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ScopeManager
    -0.54
    рович
    -0.50
     still
    -0.47
    >>,
    -0.44
    ModelSerializer
    -0.43
    ActivityCompat
    -0.42
     فريبيس
    -0.42
    -",
    -0.41
    \%,
    -0.41
    ,}
    -0.41
    POSITIVE LOGITS
     propOrder
    0.96
    webElementXpaths
    0.88
    Tikang
    0.77
    帖最后由
    0.71
    WithIOException
    0.67
     ویکی‌پدیا
    0.66
     تضيفلها
    0.63
    hasMoreElements
    0.61
     оригіналу
    0.60
     насељу
    0.60
    Activations Density 2.810%

    No Known Activations