© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 77064
    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_53_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
     Alibaba
    0.44
     alf
    0.42
     আত্মহত্যা
    0.41
     userService
    0.40
    톰
    0.40
     eft
    0.39
     forfe
    0.39
     అనుమ
    0.38
     vel
    0.38
     forfeiture
    0.38
    POSITIVE LOGITS
    xel
    0.41
    imba
    0.38
     comod
    0.37
    鬼
    0.35
    Completed
    0.35
    CHARLES
    0.34
    <0xA9>
    0.34
    antial
    0.34
    volume
    0.34
    adult
    0.34
    Activations Density 0.000%

    No Known Activations