© 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. 220398
    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
     ayak
    0.48
    </tfoot>
    0.46
    姫
    0.45
    з
    0.45
    ayak
    0.43
    槌
    0.43
    zę
    0.42
    л
    0.42
    バイ
    0.42
    -
    0.41
    POSITIVE LOGITS
     SKAction
    0.52
     Genome
    0.50
     살아
    0.50
     પાર
    0.50
     elenco
    0.49
     skapa
    0.49
     रचा
    0.49
     Blüten
    0.47
    Flavor
    0.47
     forge
    0.47
    Activations Density 0.000%

    No Known Activations