© 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. 41325
    Prev
    Next
    INDEX
    Explanations

    Roman poets and authors

    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
    в
    0.55
    㓞
    0.46
     执行
    0.43
       
    0.43
    க்கப்பட்ட
    0.42
    '.
    0.42
     ۲۰۱
    0.42
    每個
    0.41
    غيل
    0.41
    坸
    0.41
    POSITIVE LOGITS
     Fallon
    0.49
     ahorro
    0.45
    ён
    0.43
     dra
    0.43
     FAA
    0.43
     ciudad
    0.43
     रीति
    0.43
    седнев
    0.42
     costumbres
    0.42
     Pies
    0.42
    Activations Density 0.007%

    No Known Activations