© 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. 74670
    Prev
    Next
    INDEX
    Explanations

    route definition

    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
     usefulness
    0.34
     Ernst
    0.34
     Suzuki
    0.31
     outweighed
    0.31
     regional
    0.31
    Mou
    0.31
    Santo
    0.30
    樵
    0.30
    ✩
    0.30
     reversed
    0.30
    POSITIVE LOGITS
    诲
    0.35
    プレート
    0.35
    福利
    0.34
    callback
    0.34
     сцене
    0.34
     لكم
    0.33
    ให้บริการ
    0.33
     الحصه
    0.33
     রেলস্ট
    0.33
     pamię
    0.32
    Activations Density 0.005%

    No Known Activations