© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1026
    Prev
    Next
    INDEX
    Explanations

    various languages and metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_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
     thereby
    0.28
     টাক
    0.26
     behaving
    0.26
    存在的
    0.26
    IsEmpty
    0.26
     vorhanden
    0.25
    ഞ്ഞി
    0.25
     మహ
    0.25
    ٠
    0.25
     packets
    0.25
    POSITIVE LOGITS
    অম
    0.32
    搓
    0.31
     साकार
    0.29
    ],$
    0.29
    œurs
    0.29
    みんな
    0.29
    淈
    0.29
    コマ
    0.29
     gewann
    0.28
     Rá
    0.28
    Activations Density 0.023%

    No Known Activations