© 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. 25634
    Prev
    Next
    INDEX
    Explanations

    cutting/

    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
    א
    0.90
    IN
    0.84
    ال
    0.76
    ل
    0.73
    н
    0.71
    нский
    0.70
     postérieurs
    0.68
    ிகை
    0.68
    n
    0.68
    ږئ
    0.67
    POSITIVE LOGITS
    のは
    0.78
     lệch
    0.77
    letti
    0.72
    shirt
    0.71
     welcher
    0.71
     curtail
    0.69
     meltdown
    0.69
    siniz
    0.68
    आई
    0.67
     tighten
    0.66
    Activations Density 0.000%

    No Known Activations