© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38698
    Prev
    Next
    INDEX
    Explanations

    French grammar

    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_57_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
     Œ
    0.47
    Event
    0.44
     Event
    0.43
    oe
    0.40
     heur
    0.39
    arche
    0.39
    Oe
    0.39
     Oe
    0.39
    Œ
    0.38
     Tou
    0.37
    POSITIVE LOGITS
    اتب
    0.45
     sol
    0.44
     sols
    0.40
    sol
    0.38
    结束
    0.38
     bt
    0.38
     Hàn
    0.37
     handing
    0.37
     Ended
    0.37
    縷
    0.36
    Activations Density 0.004%

    No Known Activations