© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 210610
    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_10_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
    स्ट्र
    0.49
    tipo
    0.49
    ਆਂ
    0.48
    stdc
    0.47
    谐
    0.47
     rendu
    0.46
    Ρ
    0.45
    toprule
    0.45
    ቖ
    0.45
     aumentare
    0.45
    POSITIVE LOGITS
     Bacterial
    0.54
     Bookmark
    0.52
     Fragments
    0.52
     Extracts
    0.52
     Attach
    0.51
     hud
    0.50
     Besonders
    0.50
     As
    0.50
     Adapter
    0.49
    ’
    0.49
    Activations Density 0.000%

    No Known Activations