© 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. 74753
    Prev
    Next
    INDEX
    Explanations

    try again

    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
     bersifat
    0.38
    भूत
    0.36
    幼儿
    0.36
    initial
    0.36
    ės
    0.36
    úan
    0.34
    }$.)
    0.34
    不足
    0.33
    的第一
    0.33
    初の
    0.33
    POSITIVE LOGITS
     conveniently
    0.42
     cuenta
    0.41
     सारा
    0.40
     avoiding
    0.40
     vodka
    0.39
    送料無料
    0.38
     lira
    0.38
     Carmichael
    0.38
     merkle
    0.38
     طريق
    0.38
    Activations Density 0.001%

    No Known Activations