© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62550
    Prev
    Next
    INDEX
    Explanations

    able to

    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_11_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
    ت
    0.82
    on
    0.74
    ки
    0.70
    ри
    0.69
    тинг
    0.67
    odikwa
    0.67
    baiki
    0.67
     eukaryotes
    0.66
    даго
    0.65
    بیداری
    0.65
    POSITIVE LOGITS
     I
    0.77
     In
    0.70
     It
    0.68
     WITH
    0.67
    OU
    0.64
    In
    0.63
     September
    0.61
     OF
    0.60
     welchen
    0.60
     পাঁচ
    0.59
    Activations Density 0.060%

    No Known Activations