© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198163
    Prev
    Next
    INDEX
    Explanations

    literature, novels

    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
    写
    0.53
     작성
    0.53
     geschrieben
    0.53
     نوشته
    0.52
     write
    0.50
     writing
    0.49
     written
    0.49
     scrittura
    0.48
    เขียน
    0.47
     Write
    0.47
    POSITIVE LOGITS
     classical
    0.39
    othed
    0.39
     immigrant
    0.38
    襯
    0.37
     knitted
    0.37
    鉉
    0.37
     novels
    0.37
     Classical
    0.37
     ܡ
    0.36
     মাই
    0.36
    Activations Density 0.001%

    No Known Activations