© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 247977
    Prev
    Next
    INDEX
    Explanations

    requisites

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    !!!!!!!!!!!!!!!!
    0.67
    s
    0.64
    !!!!!!!!
    0.61
    !!!!!!
    0.61
    !!!!!!!
    0.60
    いる
    0.44
    ی
    0.44
    %%%%%%%%
    0.41
    sav
    0.40
    ों
    0.39
    POSITIVE LOGITS
    tedir
    0.50
    ნობ
    0.42
    ＿
    0.39
    রায়
    0.38
    häuse
    0.37
    っては
    0.37
    версите
    0.36
    ﹌
    0.36
    ষ্ঠান
    0.36
    ड़ने
    0.36
    Activations Density 0.157%

    No Known Activations