© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56530
    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_11_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
    婀
    0.57
     комплекса
    0.56
     الفصل
    0.54
     достовер
    0.48
    集群
    0.48
    徫
    0.46
    軟件
    0.46
     அரசியல்
    0.46
     تطبيق
    0.45
    瑷
    0.45
    POSITIVE LOGITS
    스
    0.48
    butene
    0.47
     shown
    0.46
     is
    0.45
     jumped
    0.45
    field
    0.45
    은
    0.45
     hits
    0.45
    राल
    0.45
     disf
    0.45
    Activations Density 0.000%

    No Known Activations