© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25576
    Prev
    Next
    INDEX
    Explanations

    image markdown or math expressions with l/n

    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_10_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
    ة
    0.79
    مر
    0.73
    на
    0.72
    й
    0.70
    раз
    0.68
    وية
    0.67
    The
    0.64
    z
    0.64
    ى
    0.63
    от
    0.62
    POSITIVE LOGITS
     !”
    0.50
    IN
    0.49
     IFN
    0.49
    ICON
    0.49
    ȟ
    0.48
    HEIM
    0.48
    !”,
    0.47
    in
    0.47
     sings
    0.47
     ફિલ્
    0.47
    Activations Density 0.000%

    No Known Activations