© 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. 108619
    Prev
    Next
    INDEX
    Explanations

    นะครับ and นะคะ

    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
    ק
    1.37
    1.27
    s
    1.19
    j
    1.14
    with
    1.13
    uction
    1.13
    т
    1.13
    ség
    1.12
    ،
    1.11
    tweets
    1.10
    POSITIVE LOGITS
    ра
    1.49
     to
    1.46
    ست
    1.18
    できる
    1.09
    5
    1.09
    した
    1.07
     čak
    1.07
     (
    1.04
    "。
    1.02
    ,
    1.02
    Activations Density 0.000%

    No Known Activations