© 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. 23880
    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
    to
    0.54
    자인
    0.50
    藐
    0.46
    bindingFields
    0.46
     competenze
    0.46
    processing
    0.46
    噙
    0.46
     दमखम
    0.45
    baixo
    0.45
    punkt
    0.44
    POSITIVE LOGITS
     coupons
    0.61
     k
    0.58
     illumination
    0.55
     isom
    0.52
     goats
    0.52
     npc
    0.51
     lemon
    0.51
     stocks
    0.50
     Aquarium
    0.50
     coupon
    0.50
    Activations Density 0.000%

    No Known Activations