© 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. 81103
    Prev
    Next
    INDEX
    Explanations

    chess notation or names like McKnight

    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
    ியே
    0.39
     مخ
    0.38
     MenuView
    0.37
     TCE
    0.37
    伦
    0.36
     ننوت
    0.36
    <unused2044>
    0.36
     ঘন
    0.35
    eal
    0.35
    隐
    0.34
    POSITIVE LOGITS
     ہمارے
    0.41
    rop
    0.41
    流れ
    0.40
    agr
    0.38
     Anu
    0.38
    ུ་
    0.38
     наша
    0.37
    <unused40>
    0.37
     কাহারও
    0.37
    Cartoon
    0.36
    Activations Density 0.012%

    No Known Activations