© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205529
    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_20_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
    list
    0.48
    ȱ
    0.48
    on
    0.46
    lash
    0.46
    stub
    0.44
    set
    0.44
    anza
    0.44
    beard
    0.43
    scoreboard
    0.43
    dust
    0.43
    POSITIVE LOGITS
     appropriateness
    0.53
     numberWithFloat
    0.53
    \|_{\
    0.50
     princes
    0.50
     backgroundColor
    0.48
     œuvres
    0.47
     ChangeNotifier
    0.46
     póź
    0.46
     gunung
    0.46
     familias
    0.46
    Activations Density 0.000%

    No Known Activations