© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43752
    Prev
    Next
    INDEX
    Explanations

    Makoto

    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_3_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
    洺
    0.61
    daten
    0.61
    тни
    0.61
    ့်
    0.57
    eron
    0.57
    ر
    0.56
    dlj
    0.54
    zzel
    0.54
    deps
    0.53
    يّ
    0.53
    POSITIVE LOGITS
    یت
    0.93
    ید
    0.86
    ang
    0.76
     pikiran
    0.73
    に
    0.71
     of
    0.70
    ﺔ
    0.68
     absoluto
    0.66
    異なる
    0.66
     }\
    0.63
    Activations Density 0.001%

    No Known Activations