© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44512
    Prev
    Next
    INDEX
    Explanations

    same name

    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_13_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
    Sh
    0.58
    Point
    0.56
    Way
    0.56
    F
    0.55
    Except
    0.54
    Lin
    0.54
    Hearing
    0.54
    To
    0.53
    Acting
    0.52
    Paulo
    0.52
    POSITIVE LOGITS
     eponym
    0.53
    ारा
    0.51
     asem
    0.50
    єднання
    0.48
     genere
    0.48
     {
    0.48
     offended
    0.48
     trasform
    0.47
     eponymous
    0.47
     použí
    0.46
    Activations Density 0.020%

    No Known Activations