© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 200469
    Prev
    Next
    INDEX
    Explanations

    non-English characters and particles

    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_6_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
    ر
    1.46
     consejos
    1.30
     młod
    1.16
    ו
    1.16
    ために
    1.10
     rápido
    1.10
     médias
    1.10
    يارات
    1.09
     trám
    1.06
    ா
    1.06
    POSITIVE LOGITS
    '
    1.20
    ra
    1.12
    ’
    1.10
    de
    1.09
    den
    1.07
    da
    1.06
    al
    1.05
     (
    1.02
    ren
    1.02
    s
    1.02
    Activations Density 0.003%

    No Known Activations