© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 5115
    Prev
    Next
    INDEX
    Explanations

    java code imports, array declarations, and related syntax

    oai_token-act-pair · gemini-2.0-flash

    semicolon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    medium
    -0.56
    veden
    -0.56
    RIST
    -0.55
    +:+
    -0.55
     MEDIUM
    -0.53
    uesia
    -0.52
     Acknowled
    -0.51
    出版年
    -0.51
     kasarigan
    -0.50
     للاسماء
    -0.50
    POSITIVE LOGITS
    énario
    0.65
     ModelExpression
    0.61
    GOTREF
    0.57
    Зноскі
    0.57
    ANTLR
    0.56
    propTypes
    0.53
    ConstraintMaker
    0.52
     Audiodateien
    0.52
     الرياضيه
    0.52
    ichtete
    0.51
    Activations Density 0.912%

    No Known Activations