© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107775
    Prev
    Next
    INDEX
    Explanations

    Kashmiri and Hindi/Urdu 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_2_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
    ன்
    0.80
    ТИ
    0.76
    션
    0.76
    член
    0.76
     nhàng
    0.76
     ול
    0.75
    \|,
    0.75
    ップ
    0.74
    ッコ
    0.74
    체가
    0.73
    POSITIVE LOGITS
    s
    1.77
     on
    1.62
     in
    1.19
    r
    1.11
    d
    1.07
    ات
    1.03
    in
    1.02
    h
    1.00
    是
    1.00
    on
    0.99
    Activations Density 0.000%

    No Known Activations