© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36838
    Prev
    Next
    INDEX
    Explanations

    ordered lists or html lists

    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_31_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
     가장
    0.37
    )+(
    0.37
     رپور
    0.36
    )+
    0.36
    ากาศ
    0.36
     aliv
    0.35
    USS
    0.35
    زة
    0.34
    峤
    0.34
     titration
    0.34
    POSITIVE LOGITS
     Def
    0.39
     Déf
    0.36
    жений
    0.36
     Zamb
    0.35
     Expressway
    0.34
     Dynam
    0.34
     مرة
    0.34
     Ltd
    0.34
     Kor
    0.33
     Zam
    0.33
    Activations Density 0.009%

    No Known Activations