© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129076
    Prev
    Next
    INDEX
    Explanations

    adverbial suffixes (-ly, -ton, -ia)

    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_1_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
    ни
    1.39
    of
    1.25
    та
    1.23
    ли
    1.19
    ור
    1.16
    त
    1.13
    x
    1.11
    но
    1.09
    є
    1.09
    т
    1.07
    POSITIVE LOGITS
    '
    0.99
    AY
    0.88
    他的
    0.83
    A
    0.79
    스가
    0.77
    表示
    0.76
    kova
    0.75
    沽
    0.74
    くん
    0.73
    这个
    0.72
    Activations Density 0.001%

    No Known Activations