© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200369
    Prev
    Next
    INDEX
    Explanations

    crossword puzzles

    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
    荅
    0.43
     answer
    0.40
    ना
    0.40
    唋
    0.39
     Leop
    0.39
    漢
    0.38
     نا
    0.38
     लह
    0.37
     deduct
    0.37
     traditionally
    0.37
    POSITIVE LOGITS
     Connor
    0.39
    คองโก
    0.39
    Connor
    0.38
     Nel
    0.36
    énie
    0.35
    úsc
    0.35
     ভগবান
    0.34
     ભગવાન
    0.34
     Ster
    0.34
     เลย
    0.34
    Activations Density 0.001%

    No Known Activations