© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 214114
    Prev
    Next
    INDEX
    Explanations

    elegant

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     wv
    0.45
    过去
    0.40
    Ћ
    0.39
    oules
    0.39
     पढ़कर
    0.38
     Carb
    0.37
     کرکے
    0.37
     carb
    0.37
    UNUSED
    0.36
    耠
    0.36
    POSITIVE LOGITS
     elegante
    1.45
     elegant
    1.41
     élég
    1.41
     elegantes
    1.34
    elegant
    1.34
    Stylish
    1.34
     eleg
    1.32
     elegance
    1.30
    Elegant
    1.30
     Elegant
    1.29
    Activations Density 0.004%

    No Known Activations