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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10295
    Prev
    Next
    INDEX
    Explanations

    sentences where the author is speaking or referencing the reader

    oai_token-act-pair · gemini-2.0-flash

    variations of "go"

    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
    Not in Any Lists

    No Comments

    Negative Logits
    yntaxException
    -0.68
    Архівовано
    -0.60
    MigrationBuilder
    -0.57
     WebDriverWait
    -0.56
    <![
    -0.56
    ValueStyle
    -0.55
    RegressionTest
    -0.54
    esterday
    -0.54
    initComponents
    -0.53
     gradova
    -0.52
    POSITIVE LOGITS
     فريبيس
    0.62
    adlo
    0.55
     بيها
    0.54
     Вікіпе
    0.54
    شوف
    0.53
    orphism
    0.51
    παν
    0.51
     domo
    0.50
     ^(
    0.49
    例文帳に追加
    0.49
    Activations Density 0.679%

    No Known Activations