© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 150405
    Prev
    Next
    INDEX
    Explanations

    markdown heading symbol

    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_59_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
     A
    1.07
    An
    0.98
     An
    0.87
    A
    0.85
    Let
    0.67
    Sur
    0.64
    Do
    0.63
    From
    0.56
    Your
    0.52
     Let
    0.50
    POSITIVE LOGITS
     الص
    0.38
     видите
    0.38
    ഗോ
    0.37
     ऑपरेट
    0.37
     العملية
    0.37
     TYPE
    0.36
    оп
    0.36
     اسمها
    0.36
    ᱡ
    0.36
     સ્વા
    0.36
    Activations Density 0.008%

    No Known Activations