© 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-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257099
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     spirals
    0.55
    સ
    0.53
     errors
    0.51
     be
    0.50
     erros
    0.50
     pits
    0.49
     errores
    0.46
     overflow
    0.46
     behave
    0.46
     oaks
    0.46
    POSITIVE LOGITS
    
    0.47
    FREQUENCY
    0.46
    ֛
    0.46
     건축
    0.45
    Франків
    0.42
    ка
    0.42
    ูนย์
    0.42
    ्रा
    0.42
    produto
    0.42
    ре
    0.42
    Activations Density 0.000%

    No Known Activations