© 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. 82438
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     zve
    0.39
     డై
    0.38
    ujących
    0.37
    ニチ
    0.37
    远离
    0.36
     recol
    0.36
     Peny
    0.36
     j
    0.36
     ste
    0.36
     rende
    0.35
    POSITIVE LOGITS
    Chest
    0.40
     bastard
    0.38
    ärast
    0.37
    Assassin
    0.37
    ｀
    0.37
    otom
    0.37
     sö
    0.35
    usters
    0.35
    —“
    0.35
    nek
    0.35
    Activations Density 0.000%

    No Known Activations