© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108778
    Prev
    Next
    INDEX
    Explanations

    Cantonese question particle 呀

    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
    Not in Any Lists

    No Comments

    Negative Logits
    자와
    1.34
    ام
    1.27
    بيه
    1.18
    و
    1.17
     mágico
    1.09
    스와
    1.08
    h
    1.06
    리와
    1.04
    畛
    1.04
    بي
    1.02
    POSITIVE LOGITS
    la
    1.66
    one
    1.31
    ↵
    1.30
    nt
    1.29
    are
    1.29
     $
    1.23
     as
    1.13
    $
    1.12
    ,
    1.09
    the
    1.07
    Activations Density 0.000%

    No Known Activations