© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 136996
    Prev
    Next
    INDEX
    Explanations

    displaying images

    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_37_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
    UMO
    0.44
    explode
    0.39
    enable
    0.38
    populate
    0.38
    ilyl
    0.38
     ನಡೆಯ
    0.37
    摷
    0.36
    inium
    0.35
     لاب
    0.35
    জনক
    0.34
    POSITIVE LOGITS
    ๅ
    0.43
    ular
    0.42
     visibility
    0.41
     visualization
    0.39
    िकुलर
    0.38
     diapers
    0.38
     diaper
    0.37
     **
    0.37
    Ყ
    0.37
    可视化
    0.36
    Activations Density 0.001%

    No Known Activations