© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43955
    Prev
    Next
    INDEX
    Explanations

    bien sûr

    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_13_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
    ตี
    0.60
     وګټ
    0.55
    iculaire
    0.52
     تومان
    0.48
     دلار
    0.46
    ニャ
    0.46
    ы
    0.45
     simplifying
    0.45
    ફેદ
    0.45
     امتیاز
    0.44
    POSITIVE LOGITS
    żs
    0.58
    H
    0.54
     Hersteller
    0.53
    ção
    0.53
    ACT
    0.52
    VO
    0.52
    ę
    0.52
    Mor
    0.52
    第三
    0.52
    gäng
    0.52
    Activations Density 0.000%

    No Known Activations