© 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. 214518
    Prev
    Next
    INDEX
    Explanations

    Vas

    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
    饒
    0.41
    mst
    0.39
     자랑
    0.39
     mq
    0.39
    ມ
    0.38
    宍
    0.38
     hits
    0.38
    Hits
    0.38
    mData
    0.37
    ռ
    0.37
    POSITIVE LOGITS
    ud
    0.54
    hu
    0.51
    gha
    0.45
    ukur
    0.43
    u
    0.42
    ूद
    0.41
    Hu
    0.41
     ha
    0.41
    केदार
    0.41
    Hav
    0.41
    Activations Density 0.000%

    No Known Activations