© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21947
    Prev
    Next
    INDEX
    Explanations

    Japanese words

    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_56_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
    Се
    0.46
    أ
    0.44
    ඍ
    0.44
    Мі
    0.43
    في
    0.42
    எ
    0.41
    قافة
    0.40
    Пі
    0.40
    Итак
    0.40
    、
    0.40
    POSITIVE LOGITS
     ভাবে
    0.41
    勧
    0.39
    徫
    0.38
     Â
    0.37
     “,
    0.37
    眅
    0.36
    লভ
    0.36
    antina
    0.36
     “.
    0.35
    問い合わせ
    0.35
    Activations Density 0.000%

    No Known Activations