© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 83850
    Prev
    Next
    INDEX
    Explanations

    API weather data

    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_29_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
     Xác
    0.40
     Chí
    0.38
     قيمة
    0.38
     مرد
    0.38
    بلا
    0.37
     Tagore
    0.37
    按
    0.36
     ∫
    0.36
     dấu
    0.35
     θα
    0.35
    POSITIVE LOGITS
     ceremonies
    0.41
     territory
    0.39
    MILL
    0.39
     proceedings
    0.39
     procedures
    0.39
     conversions
    0.39
     reception
    0.38
    ಲಿನ
    0.38
    写真
    0.38
     cleans
    0.38
    Activations Density 0.007%

    No Known Activations