© 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. 15107
    Prev
    Next
    INDEX
    Explanations

    data fabric, data mesh

    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
    σης
    0.54
    νου
    0.48
    的
    0.46
    證
    0.46
    شن
    0.45
    تك
    0.44
    ائي
    0.44
    因
    0.44
    خت
    0.43
     gehört
    0.43
    POSITIVE LOGITS
    t
    0.64
     eternal
    0.56
     alat
    0.52
     worked
    0.50
    eternal
    0.50
     दृष्टी
    0.49
     eternally
    0.49
     ایران
    0.49
     artisan
    0.48
     rencana
    0.48
    Activations Density 0.000%

    No Known Activations