© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145866
    Prev
    Next
    INDEX
    Explanations

    words starting with "lég"

    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
    ۰
    2.02
    ς
    1.77
     ی
    1.55
    ים
    1.52
    ات
    1.48
     समेत
    1.48
    ところで
    1.47
     despicable
    1.46
     ۸
    1.44
    :
    1.43
    POSITIVE LOGITS
    ン
    1.60
    ন
    1.42
     großen
    1.32
    人
    1.32
    يل
    1.31
     späteren
    1.30
    ن
    1.29
    قي
    1.27
     kleinen
    1.27
    上
    1.22
    Activations Density 0.000%

    No Known Activations