© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194013
    Prev
    Next
    INDEX
    Explanations

    Cantor and Frege

    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_15_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
     Korea
    0.50
     Rept
    0.47
     Korean
    0.46
    лар
    0.45
    ↵↵
    0.44
    浮
    0.44
    兩
    0.43
     ABS
    0.43
    Korea
    0.43
    必
    0.43
    POSITIVE LOGITS
    aseña
    0.57
    केंसी
    0.55
    íticos
    0.55
    നില
    0.55
    salaryto
    0.53
    linkCell
    0.52
    desde
    0.52
     खिलाड़ी
    0.51
     खिलाड़ियों
    0.51
     घंटों
    0.50
    Activations Density 0.001%

    No Known Activations