© 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. 34923
    Prev
    Next
    INDEX
    Explanations

    defining services

    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
    视为
    0.72
    ｳ
    0.65
    ྥ
    0.63
    まず
    0.60
    یمو
    0.58
    orealistic
    0.57
    ربعة
    0.56
    ﾍ
    0.56
     جائے
    0.56
    か
    0.55
    POSITIVE LOGITS
     Coco
    0.56
     Comme
    0.51
     PTSD
    0.50
     Pilates
    0.49
     Coca
    0.47
    ↵↵
    0.47
     Gilead
    0.47
     mend
    0.46
     Pisces
    0.46
     Lotus
    0.45
    Activations Density 0.007%

    No Known Activations