© 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. 146279
    Prev
    Next
    INDEX
    Explanations

    non-English ending syllables

    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
    ä
    1.50
    ି
    1.47
    いる
    1.45
    設定
    1.41
    s
    1.37
    ам
    1.36
     дітей
    1.35
     is
    1.34
    ੀ
    1.34
     денег
    1.33
    POSITIVE LOGITS
     a
    1.73
    as
    1.66
    ة
    1.58
    นี่
    1.51
    a
    1.45
    ם
    1.44
    ing
    1.42
    an
    1.36
    in
    1.35
    ช่วง
    1.28
    Activations Density 0.000%

    No Known Activations