© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 19252
    Prev
    Next
    INDEX
    Explanations

    book titles and authors

    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_40_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
     pront
    0.40
    ังหวัด
    0.39
    怎么办
    0.38
     başarılı
    0.37
    ⁀
    0.37
    副
    0.36
     Albany
    0.36
     shattered
    0.36
     maest
    0.35
    ~~
    0.35
    POSITIVE LOGITS
    EMAN
    0.39
     Styl
    0.38
     FU
    0.36
     merk
    0.36
    Styl
    0.36
    styl
    0.35
     உண்டு
    0.35
    遊
    0.35
     ಮನ
    0.35
     MRI
    0.34
    Activations Density 0.030%

    No Known Activations