© 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. 78796
    Prev
    Next
    INDEX
    Explanations

    boucles in French texts

    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
    ن
    1.59
    ン
    1.41
    ться
    1.38
    می
    1.35
    จะ
    1.28
    О
    1.27
    ק
    1.24
    ing
    1.21
    िया
    1.18
    ുന്ന
    1.18
    POSITIVE LOGITS
    u
    2.14
    are
    1.77
    ot
    1.75
    i
    1.66
    z
    1.65
    ா
    1.55
    é
    1.42
    re
    1.38
    f
    1.36
    ي
    1.30
    Activations Density 0.000%

    No Known Activations