© 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. 217141
    Prev
    Next
    INDEX
    Explanations

    concurrent timing

    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
    하게
    0.68
     하게
    0.55
    aneously
    0.46
    cially
    0.44
    게
    0.43
    otically
    0.43
     있게
    0.42
    erweise
    0.42
     가게
    0.42
    urally
    0.41
    POSITIVE LOGITS
     while
    0.97
     tandis
    0.86
    while
    0.85
     Sementara
    0.77
     whilst
    0.76
     Meanwhile
    0.75
     ενώ
    0.75
    而
    0.75
     mentre
    0.74
     meanwhile
    0.73
    Activations Density 0.000%

    No Known Activations