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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5182
    Prev
    Next
    INDEX
    Explanations

    mentions of books, reading, blogs, and authors, especially if they are followed by other related terms

    oai_token-act-pair · gemini-2.0-flash

    the word "book"

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

    book

    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
    jsxFileName
    -0.49
     всему
    -0.47
     ویکی‌پدیا
    -0.45
    pkey
    -0.43
     Roskov
    -0.43
    ":[{
    -0.42
    QUID
    -0.42
     Big
    -0.41
    mappedBy
    -0.41
    clyde
    -0.40
    POSITIVE LOGITS
     שוליים
    0.73
     varargin
    0.71
     дописавши
    0.70
     Marcello
    0.69
     Haram
    0.68
    BeginInit
    0.68
    decks
    0.65
     Mauritania
    0.65
     صوتيه
    0.65
    MeasureSpec
    0.65
    Activations Density 2.987%

    No Known Activations