© 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. 176704
    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
     amélior
    0.55
     fiscales
    0.55
    舧
    0.52
    rendre
    0.50
     considérable
    0.50
    세요
    0.49
    መሳሳይ
    0.48
    ትክል
    0.48
    혔
    0.48
     internationaux
    0.47
    POSITIVE LOGITS
     ತ
    0.48
    ”
    0.46
    ate
    0.45
     улы
    0.45
     пода
    0.43
     жили
    0.43
     Clem
    0.43
    ’
    0.42
    孭
    0.42
    ల్ల
    0.42
    Activations Density 0.000%

    No Known Activations