© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58730
    Prev
    Next
    INDEX
    Explanations

    EPS and forecasts

    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_11_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
    尔
    0.37
     photoelectron
    0.36
     leftWheel
    0.35
    但我
    0.34
    ین
    0.34
     digitalisation
    0.33
     versed
    0.33
    璁
    0.33
     cero
    0.33
     aprend
    0.33
    POSITIVE LOGITS
     Athletics
    0.46
     Highlights
    0.42
     Agriculture
    0.41
     Saudi
    0.40
     Cloudy
    0.38
     Forecast
    0.38
     Appendix
    0.38
     Expect
    0.37
     wodurch
    0.37
     Schedule
    0.37
    Activations Density 0.015%

    No Known Activations