© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 83784
    Prev
    Next
    INDEX
    Explanations

    d)

    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_29_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
     (?)
    0.39
    (?)
    0.38
     genc
    0.38
     методи
    0.37
     méthod
    0.37
     presumed
    0.36
    ¹,
    0.35
    ત્તા
    0.35
     Juni
    0.34
     methodological
    0.34
    POSITIVE LOGITS
    که
    0.39
    ائي
    0.37
     পৌরসভার
    0.36
    Courier
    0.34
     会
    0.34
     Recursive
    0.34
     arxiv
    0.34
     শিশুদের
    0.33
    égard
    0.33
    להקה
    0.33
    Activations Density 0.001%

    No Known Activations