© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215733
    Prev
    Next
    INDEX
    Explanations

    non-English characters and words

    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_5_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
    д
    1.26
    ונה
    1.23
    ants
    1.14
    INE
    1.14
     can
    1.11
    स
    1.10
    ارك
    1.09
    ORK
    1.06
    تي
    1.06
    se
    1.02
    POSITIVE LOGITS
    by
    1.16
     presentes
    1.14
     cuidados
    1.09
    ও
    1.09
    在
    1.08
    ન
    1.07
    for
    1.03
    एस
    1.00
    or
    0.98
    ло
    0.97
    Activations Density 0.000%

    No Known Activations