© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 226115
    Prev
    Next
    INDEX
    Explanations

    French articles and prepositions

    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_10_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
    स्ट
    0.72
    崧
    0.70
     As
    0.64
    ss
    0.64
    رسٹ
    0.63
    モンスター
    0.62
     and
    0.61
    イ
    0.61
    ip
    0.61
    セ
    0.61
    POSITIVE LOGITS
    a
    0.94
    ה
    0.85
    ية
    0.77
     de
    0.74
     werde
    0.73
     де
    0.70
    zelfde
    0.70
    ائية
    0.66
    يند
    0.66
    اتي
    0.65
    Activations Density 0.000%

    No Known Activations