© 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
    2. Gemma-3-27B-IT
    3. 46-GEMMASCOPE-2-TRANSCODER-262K
    4. 140278
    Prev
    Next
    INDEX
    Explanations

    Chinese poetry

    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_46_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
     Cir
    0.45
     Kirk
    0.44
     cir
    0.43
    Cir
    0.43
     zirconia
    0.42
     던
    0.41
     Ed
    0.41
     Horse
    0.40
     Cosmetic
    0.39
     Chir
    0.38
    POSITIVE LOGITS
     শাসন
    0.42
    锤
    0.40
     Christendom
    0.38
    Semitism
    0.38
    SU
    0.38
    Ee
    0.37
     Реги
    0.37
    錘
    0.37
     પતિ
    0.37
    ុំ
    0.37
    Activations Density 0.002%

    No Known Activations