© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48594
    Prev
    Next
    INDEX
    Explanations

    educational institutions and academies

    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
    ﺯ
    0.78
    ﺭ
    0.77
    ﺒ
    0.76
     planis
    0.75
    ﻨ
    0.73
     settimana
    0.73
     commerciales
    0.70
    ﻔ
    0.68
     byl
    0.67
     contrat
    0.67
    POSITIVE LOGITS
     Academy
    0.73
    ut
    0.66
    ot
    0.66
    ol
    0.61
    stances
    0.58
    ro
    0.57
    ↵
    0.56
    ul
    0.56
    ra
    0.55
    ur
    0.54
    Activations Density 0.010%

    No Known Activations