© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 47191
    Prev
    Next
    INDEX
    Explanations

    Khruangbin and Thai language

    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_3_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
    0.71
    r
    0.68
    dni
    0.68
    ER
    0.65
    LE
    0.64
    ങ്ങൾ
    0.62
    stion
    0.60
    V
    0.60
    parameter
    0.59
    ?
    0.59
    POSITIVE LOGITS
    ח
    0.69
    ш
    0.68
    जुर्ग
    0.68
    ش
    0.66
    ни
    0.64
     pertence
    0.64
    を有
    0.62
    an
    0.62
     chảy
    0.62
     regenerating
    0.61
    Activations Density 0.000%

    No Known Activations