© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15169
    Prev
    Next
    INDEX
    Explanations

    atomism and yoga

    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_13_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
    ARA
    0.48
     H
    0.45
    Dam
    0.45
     تحتاج
    0.43
     reparar
    0.43
    }=(\
    0.42
    F
    0.42
    ADE
    0.41
    W
    0.41
    Ḫ
    0.41
    POSITIVE LOGITS
     innervation
    0.49
     undervalued
    0.48
     inaccuracies
    0.47
    ributes
    0.47
     unrecognized
    0.47
    щие
    0.46
     inflammatory
    0.44
     व्यंजन
    0.44
    ioniert
    0.43
     inflationary
    0.43
    Activations Density 0.013%

    No Known Activations