© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78026
    Prev
    Next
    INDEX
    Explanations

    size

    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_53_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
     Ambris
    0.40
    🈺
    0.38
    żliw
    0.37
    忤
    0.37
     graphing
    0.37
    뷸
    0.36
     የማ
    0.36
    かと
    0.36
    🚱
    0.36
    ുകൊണ്ടാണ്
    0.35
    POSITIVE LOGITS
    uli
    0.41
     кра
    0.39
     rossa
    0.37
     gev
    0.37
    enig
    0.36
     имени
    0.35
    воз
    0.35
     lp
    0.34
     kg
    0.34
     ION
    0.34
    Activations Density 0.001%

    No Known Activations