© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 2920
    Prev
    Next
    INDEX
    Explanations

    the word "domestic" and other words associated with the home or country

    oai_token-act-pair · gemini-2.0-flash

    domestic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     للاسماء
    -1.57
    principalTable
    -1.57
     виправивши
    -1.53
    InjectAttribute
    -1.50
    MigrationBuilder
    -1.41
    NameInMap
    -1.40
    RenderAtEndOf
    -1.38
     Савезне
    -1.35
     فريبيس
    -1.35
    Personensuche
    -1.34
    POSITIVE LOGITS
     
    0.94
    y
    0.87
    a
    0.79
    er
    0.77
    o
    0.77
    ↵
    0.77
     still
    0.73
    ,
    0.72
    ing
    0.71
     (
    0.71
    Activations Density 2.062%

    No Known Activations