© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3024
    Prev
    Next
    INDEX
    Explanations

    mentions of musical groups and/or albums

    oai_token-act-pair · gemini-2.0-flash

    band

    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
    RefNanny
    -0.56
    Water
    -0.54
     diting
    -0.54
     LEVELS
    -0.53
     Wet
    -0.50
    bode
    -0.50
     WATER
    -0.49
     Water
    -0.48
     Wikiseite
    -0.48
     REGARD
    -0.48
    POSITIVE LOGITS
     للاسماء
    0.69
    DoubleQuotes
    0.60
    RegressionTest
    0.56
    randomUUID
    0.50
    migrationBuilder
    0.49
    JspWriter
    0.48
     дописавши
    0.47
    Tikang
    0.46
     Rhymes
    0.46
    hasMoreElements
    0.46
    Activations Density 0.266%

    No Known Activations