© 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. 13528
    Prev
    Next
    INDEX
    Explanations

    words, phrases, or concepts related to government programs, social issues, and policy

    oai_token-act-pair · gemini-2.0-flash

    government and social programs

    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
    MigrationBuilder
    -0.98
    +:+
    -0.94
    .*")]
    -0.86
     purpoſe
    -0.84
     Houſe
    -0.84
     houſe
    -0.84
     ainfi
    -0.81
    featureID
    -0.80
     ویکی‌پدیا
    -0.80
     tartalomajánló
    -0.78
    POSITIVE LOGITS
     
    0.70
      
    0.62
     in
    0.55
     die
    0.52
     $
    0.52
     "
    0.50
     per
    0.50
     E
    0.50
     Ver
    0.49
     an
    0.49
    Activations Density 0.601%

    No Known Activations