© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54763
    Prev
    Next
    INDEX
    Explanations

    key is and value

    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_30_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
     dibagi
    0.36
    狎
    0.32
     darwin
    0.32
    өлү
    0.31
    ಿದ್ದರು
    0.31
    первых
    0.31
    എസ്
    0.31
     கெல்வின்
    0.30
    ǰ
    0.30
    並沒有
    0.30
    POSITIVE LOGITS
    リート
    0.28
     cheer
    0.28
    体
    0.28
     servent
    0.27
     figures
    0.27
     kana
    0.27
     Emanuel
    0.27
    巴
    0.27
     shop
    0.27
    abbe
    0.26
    Activations Density 0.000%

    No Known Activations