© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11478
    Prev
    Next
    INDEX
    Explanations

    Chinese, dictionaries, Anki, JLPT, wikipedia

    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_40_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
     सिंप
    0.40
     অনুবাদ
    0.39
    дун
    0.39
     Feedback
    0.37
     ريا
    0.37
     уг
    0.36
    Გ
    0.36
     Translate
    0.35
    tg
    0.35
     Translated
    0.35
    POSITIVE LOGITS
    搜索
    0.40
    螫
    0.40
     Mio
    0.39
     SDL
    0.39
     decks
    0.39
    Dict
    0.38
    平行
    0.38
    Purg
    0.38
     SPDX
    0.37
     Apert
    0.37
    Activations Density 0.140%

    No Known Activations