© 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. 8872
    Prev
    Next
    INDEX
    Explanations

    doctoral programs and degrees

    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
    Not in Any Lists

    No Comments

    Negative Logits
     め
    0.63
    keme
    0.55
     wholly
    0.52
     distinta
    0.51
     Bauern
    0.51
    beza
    0.51
     הד
    0.50
     почина
    0.50
    regor
    0.49
    thew
    0.48
    POSITIVE LOGITS
    无
    0.48
    反馈
    0.45
     creases
    0.45
    上
    0.45
    内置
    0.45
    杀死
    0.45
    ू
    0.44
     Public
    0.44
    ພວກເຮ
    0.44
    সাল
    0.44
    Activations Density 0.004%

    No Known Activations