© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218476
    Prev
    Next
    INDEX
    Explanations

    if __name__ == '__main__': app.run

    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_31_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
    дца
    0.40
    MEAS
    0.38
    piel
    0.38
     Ell
    0.37
    icoter
    0.37
     সাই
    0.37
     جی
    0.36
    <0xC2>
    0.36
     ज्योतिष
    0.36
    Eyes
    0.36
    POSITIVE LOGITS
     అనుమ
    0.40
    是否
    0.40
     arab
    0.40
     trasporto
    0.40
     shipped
    0.39
     mejores
    0.38
     фаса
    0.38
     migliori
    0.38
     prisma
    0.37
     facade
    0.37
    Activations Density 0.000%

    No Known Activations