© 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. 16345
    Prev
    Next
    INDEX
    Explanations

    words associated with both literal and metaphorical drawing.

    oai_token-act-pair · gemini-2.0-flash

    drawing

    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
     OnInit
    -0.60
     présidentielle
    -0.57
    bulin
    -0.56
    ionali
    -0.55
    QMessageBox
    -0.54
     newOwner
    -0.53
    онер
    -0.52
    Palmar
    -0.52
     lente
    -0.51
    fromnode
    -0.51
    POSITIVE LOGITS
     drawings
    0.96
     DRAWINGS
    0.93
     Drawings
    0.92
     drawing
    0.89
     Drawing
    0.85
     drawn
    0.85
    Drawing
    0.79
     Draws
    0.78
    draw
    0.78
     DRAWING
    0.77
    Activations Density 1.783%

    No Known Activations