© 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. 130634
    Prev
    Next
    INDEX
    Explanations

    Taiwan

    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
    ﾆ
    0.42
    DataDiv
    0.39
     Pentagon
    0.37
     Strategic
    0.36
    Dav
    0.36
     Dav
    0.36
    畕
    0.36
     동
    0.35
    옥
    0.35
     discriminate
    0.35
    POSITIVE LOGITS
     Ta
    0.60
    Ta
    0.57
    Tay
    0.53
     Tai
    0.52
    Taylor
    0.52
    Tai
    0.52
     Tay
    0.48
     Taylor
    0.48
     taylor
    0.47
     Тай
    0.46
    Activations Density 0.001%

    No Known Activations