© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6173
    Prev
    Next
    INDEX
    Explanations

    Scrum, air, Files, of, of, OS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    [
    0.49
    (
    0.46
    Но
    0.42
    ה
    0.41
    உ
    0.40
    제
    0.40
    At
    0.40
    То
    0.39
    As
    0.39
    Вы
    0.39
    POSITIVE LOGITS
    ى
    0.57
    €™
    0.51
     daarmee
    0.50
     $%
    0.49
    ៉
    0.49
    é
    0.48
    atchewan
    0.48
     palvel
    0.47
     kurt
    0.47
     pudi
    0.47
    Activations Density 0.239%

    No Known Activations