© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39834
    Prev
    Next
    INDEX
    Explanations

    BAZOOKA HQ

    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_3_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
    다
    0.64
    čke
    0.61
    ジェクト
    0.61
    Barcelona
    0.60
     Barcelone
    0.58
    ть
    0.57
    sequences
    0.57
    ാണ്
    0.55
    asjonen
    0.55
    ند
    0.54
    POSITIVE LOGITS
    AN
    0.72
     جي
    0.70
     მ
    0.67
    ;
    0.66
     да
    0.66
     في
    0.65
     pulpit
    0.65
    {
    0.65
    \,\
    0.64
    IR
    0.63
    Activations Density 0.001%

    No Known Activations