© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56898
    Prev
    Next
    INDEX
    Explanations

    Komusō monks and souke

    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_11_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
    Rec
    0.43
    㕮
    0.40
    हरी
    0.40
    Ħ
    0.39
    umim
    0.39
    Nad
    0.39
    烀
    0.39
    ूक
    0.38
    閫
    0.38
    瀵
    0.38
    POSITIVE LOGITS
    ⃙
    0.47
    ：
    0.44
    <0x99>
    0.42
     convincingly
    0.42
    ureate
    0.40
     kto
    0.40
     intently
    0.40
     féidir
    0.40
     htons
    0.39
     يك
    0.39
    Activations Density 0.003%

    No Known Activations