© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 155265
    Prev
    Next
    INDEX
    Explanations

    get

    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_50_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
     us
    0.44
    瘩
    0.38
     Laub
    0.37
     adresu
    0.36
    Ment
    0.36
     Doklady
    0.36
     Duck
    0.35
    kart
    0.35
    sluš
    0.35
     綿
    0.35
    POSITIVE LOGITS
    бин
    0.43
    삿
    0.39
    ś
    0.36
    nb
    0.35
    δι
    0.34
    বাদে
    0.34
     err
    0.34
    шни
    0.34
    oree
    0.34
    }\|\
    0.34
    Activations Density 0.003%

    No Known Activations