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

    Neuronpedia

    Jacobian LensNEW
    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. 45005
    Prev
    Next
    INDEX
    Explanations

    MIIMIC-III MIMIC-IV MIMIC-Webst

    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
    ни
    0.82
    t
    0.79
    ра
    0.73
    что
    0.71
    It
    0.68
    ι
    0.68
    あ
    0.66
    נ
    0.63
    но
    0.61
    т
    0.60
    POSITIVE LOGITS
    el
    0.70
    ↵↵
    0.65
     private
    0.61
     in
    0.61
     σε
    0.60
    am
    0.59
     facilities
    0.59
     needless
    0.59
     dishes
    0.59
     markets
    0.56
    Activations Density 0.007%

    No Known Activations