© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84031
    Prev
    Next
    INDEX
    Explanations

    Thai words (สรร) and foreign words (utan)

    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_0_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
     a
    1.87
    ri
    1.61
    .
    1.55
    at
    1.54
     been
    1.49
    3
    1.48
    ct
    1.40
     as
    1.38
     at
    1.38
    ut
    1.34
    POSITIVE LOGITS
    С
    1.73
    는
    1.73
    は
    1.70
    是
    1.58
    ان
    1.54
    ي
    1.45
    ת
    1.44
    И
    1.44
    ו
    1.41
    其他
    1.38
    Activations Density 0.001%

    No Known Activations