© 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. 124729
    Prev
    Next
    INDEX
    Explanations

    macular degeneration

    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
    of
    0.73
    یده
    0.66
    ς
    0.64
     I
    0.62
     ی
    0.62
    지만
    0.60
     सभ्यता
    0.58
    یش
    0.58
     زی
    0.58
    有名な
    0.57
    POSITIVE LOGITS
    ت
    0.70
    ко
    0.66
    ي
    0.65
    i
    0.63
     eind
    0.62
     الأ
    0.61
    قي
    0.60
    tr
    0.58
     ahorrar
    0.58
    c
    0.57
    Activations Density 0.000%

    No Known Activations