© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 133026
    Prev
    Next
    INDEX
    Explanations

    [

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     ピン
    0.36
    潺
    0.35
     electrolytic
    0.34
    Akt
    0.34
    الع
    0.33
    ற்ச
    0.33
    함을
    0.33
    accord
    0.33
    luc
    0.32
    Ug
    0.31
    POSITIVE LOGITS
    ｘ
    0.39
     į
    0.38
     IW
    0.38
    ზ
    0.37
     blanches
    0.36
     opl
    0.36
     Combs
    0.36
     गुला
    0.36
    ʟ
    0.35
     karm
    0.35
    Activations Density 0.001%

    No Known Activations