© 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-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 256537
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ❇
    1.11
     wigs
    1.06
    😼
    1.06
    !!!");
    1.05
     budgeted
    1.02
    ◙
    1.01
     preterm
    1.01
    😦
    1.00
     layoffs
    1.00
    
    1.00
    POSITIVE LOGITS
     montrent
    0.83
    лы
    0.83
    AL
    0.78
     milliers
    0.78
    ग्
    0.77
    ין
    0.76
     custodian
    0.75
     trova
    0.75
     此
    0.73
     denna
    0.72
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.