© 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. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 2924
    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_12_width_16k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    čaj
    0.56
    ടതി
    0.55
     remembrance
    0.55
    
    0.55
     السابع
    0.55
    PARATION
    0.55
     знаходи
    0.54
    烂
    0.54
    tempat
    0.54
     açı
    0.53
    POSITIVE LOGITS
    //=
    0.47
     protocol
    0.44
     altera
    0.44
     Signore
    0.44
     bistouri
    0.43
     Messrs
    0.42
     Herren
    0.42
    Me
    0.42
     counterpart
    0.41
    ্নান
    0.41
    Activations Density 0.026%

    No Known Activations