© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 142576
    Prev
    Next
    INDEX
    Explanations

    prescription, lenses, or frames

    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_12_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
     آ
    0.54
     elution
    0.48
    immon
    0.46
    ﺪ
    0.46
     종료
    0.45
     sheltered
    0.45
    ز
    0.44
    癢
    0.44
    ิ้ง
    0.44
     Flü
    0.44
    POSITIVE LOGITS
     sadece
    0.49
    毂
    0.49
     শুধুমাত্র
    0.48
    csak
    0.47
    ড়াতে
    0.46
     collide
    0.46
    lak
    0.46
    நப
    0.46
     différente
    0.45
     സാഹചര്യ
    0.45
    Activations Density 0.001%

    No Known Activations