© 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. 8746
    Prev
    Next
    INDEX
    Explanations

    linen cloth / dress / head / covering

    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
    ツ
    0.48
    イツ
    0.47
     скон
    0.46
     to
    0.46
     Including
    0.43
    学校
    0.42
     مدارس
    0.42
    ¿
    0.42
    ized
    0.41
    fü
    0.41
    POSITIVE LOGITS
    ut
    0.57
    getDrawable
    0.46
    Ќ
    0.46
    EC
    0.46
     bodysuit
    0.45
     gauze
    0.45
     Grup
    0.44
    帛
    0.44
     Trabajo
    0.44
    骼
    0.43
    Activations Density 0.033%

    No Known Activations