© 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. 178189
    Prev
    Next
    INDEX
    Explanations

    items or concepts

    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
    Down
    0.44
     kaas
    0.42
     झा
    0.42
     kü
    0.40
    Kul
    0.39
    拉
    0.39
     sur
    0.38
     xe
    0.38
     pi
    0.38
    реди
    0.38
    POSITIVE LOGITS
     পরিস
    0.39
     Revolt
    0.38
     Rice
    0.38
    啬
    0.37
     عبدال
    0.37
     MPS
    0.37
    Rice
    0.36
    ้วน
    0.36
    $-[
    0.35
    udal
    0.34
    Activations Density 0.000%

    No Known Activations