© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4617
    Prev
    Next
    INDEX
    Explanations

    collection operations (Max, Count, Select)

    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_39_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
    uspended
    0.45
    还原
    0.43
    𒅁
    0.43
    SEVERE
    0.42
    டுப
    0.40
     omin
    0.40
    இர
    0.39
     கடும்
    0.39
    芏
    0.39
    imsu
    0.39
    POSITIVE LOGITS
     super
    0.41
     Myr
    0.39
     संघा
    0.37
    வ்
    0.37
    擂
    0.36
    Skip
    0.36
    $(
    0.36
     ज्यो
    0.36
    かく
    0.36
    toArray
    0.35
    Activations Density 0.012%

    No Known Activations