© 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. 200842
    Prev
    Next
    INDEX
    Explanations

    Shi

    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
     ሳ
    0.45
     zabud
    0.40
    antil
    0.38
     lồ
    0.38
    ździe
    0.38
    zan
    0.38
     اینڈ
    0.37
    ܙ
    0.37
     অসুর
    0.37
    rza
    0.37
    POSITIVE LOGITS
     Gli
    0.40
    Gli
    0.39
     हळ
    0.39
     Pipeline
    0.39
    ulis
    0.38
    Pipeline
    0.37
    임
    0.37
    ди
    0.36
     gli
    0.36
     উৎসাহ
    0.36
    Activations Density 0.000%

    No Known Activations