© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10284
    Prev
    Next
    INDEX
    Explanations

    mentions of "United States of America."

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ⓧ
    -0.87
    usermodel
    -0.54
     Ska
    -0.51
    addComponent
    -0.49
     Conference
    -0.46
    reps
    -0.46
    פו
    -0.46
     Pog
    -0.45
     corps
    -0.45
    artments
    -0.44
    POSITIVE LOGITS
     America
    0.98
    America
    0.89
     AMERICA
    0.85
    america
    0.77
     america
    0.77
     дописавши
    0.72
    MigrationBuilder
    0.66
     HttpNotFound
    0.65
    américa
    0.64
     América
    0.63
    Activations Density 1.242%

    No Known Activations