© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53838
    Prev
    Next
    INDEX
    Explanations

    answer format instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     たち
    0.37
    хать
    0.37
     तेव्हा
    0.36
     това
    0.35
     अपील
    0.35
     greco
    0.35
    津
    0.35
    ഷ
    0.34
     κατα
    0.34
     negotiating
    0.34
    POSITIVE LOGITS
     answers
    0.43
    Answers
    0.38
    ivariable
    0.38
    पृथ्वी
    0.36
     '='
    0.36
    Task
    0.36
    問題を
    0.36
    answers
    0.35
     problemi
    0.35
    क्यू
    0.34
    Activations Density 0.002%

    No Known Activations