© 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. 130966
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     ईश्वर
    0.41
    स्वर
    0.41
    ວຍ
    0.39
    മുഖ
    0.39
    悅
    0.38
    砶
    0.38
     تن
    0.38
     ঈশ্বর
    0.38
    ळे
    0.38
    स्वरूप
    0.38
    POSITIVE LOGITS
     Marie
    0.42
     doo
    0.41
    Marie
    0.40
     Kos
    0.39
     dynamic
    0.38
     जेन
    0.38
     Wilbur
    0.38
    Ae
    0.37
     marie
    0.37
    鞑
    0.37
    Activations Density 0.000%

    No Known Activations