© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17490
    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_40_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
     부탁
    0.40
     Interpreter
    0.40
    娯
    0.39
    Interpol
    0.38
     формирование
    0.38
    reporting
    0.37
    ুদ
    0.37
     flexDirection
    0.36
     misinterpreted
    0.36
    舘
    0.36
    POSITIVE LOGITS
    makefile
    0.40
     Schaden
    0.40
     nắm
    0.39
    楔
    0.37
    আই
    0.37
     hozz
    0.37
    కో
    0.36
    ća
    0.35
    лама
    0.35
    ี้ยว
    0.35
    Activations Density 0.000%

    No Known Activations