© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12285
    Prev
    Next
    INDEX
    Explanations

    mentions of North Korea, Russia and the names of political leaders

    oai_token-act-pair · gemini-2.0-flash

    Jong

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    COUVER
    -0.40
     d
    -0.36
     قص
    -0.35
    multer
    -0.35
    newcommand
    -0.35
    asable
    -0.34
     simply
    -0.34
    principalColumn
    -0.33
    use
    -0.32
    ipro
    -0.32
    POSITIVE LOGITS
    +#+
    0.83
     Habana
    0.82
    Cuban
    0.79
     Cuban
    0.77
     Maduro
    0.73
    iddhar
    0.73
    amaño
    0.71
    openzeppelin
    0.70
    
    0.70
    RegressionTest
    0.70
    Activations Density 0.641%

    No Known Activations