© 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. 43833
    Prev
    Next
    INDEX
    Explanations

    looks like

    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
    á
    0.87
    ة
    0.87
    ية
    0.85
    ä
    0.79
    ing
    0.74
     be
    0.74
     on
    0.74
    ')
    0.67
    證
    0.64
    ný
    0.63
    POSITIVE LOGITS
    菰
    0.70
     άλλα
    0.62
     кораб
    0.61
     gota
    0.61
     "."
    0.60
    ッテリー
    0.60
    lty
    0.60
     expts
    0.60
    жают
    0.60
     Сури
    0.59
    Activations Density 0.002%

    No Known Activations