© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143573
    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_46_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
    (""))
    0.43
    goes
    0.42
     Filament
    0.39
     går
    0.38
     filo
    0.37
    seated
    0.37
     goes
    0.36
     ه
    0.36
    by
    0.35
    lac
    0.35
    POSITIVE LOGITS
    ጢ
    0.39
     изуча
    0.39
     datasets
    0.39
    垟
    0.38
     পেরে
    0.38
    sigh
    0.37
    मेंट
    0.37
     sigh
    0.37
     ገን
    0.37
    Asalamualaikum
    0.37
    Activations Density 0.000%

    No Known Activations