© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13219
    Prev
    Next
    INDEX
    Explanations

    PyQt gui framework

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    𝘷
    0.39
    ソッド
    0.38
    asonic
    0.35
    ijd
    0.34
    経営
    0.34
     یق
    0.34
     पप्पू
    0.33
     হ্যান্ড
    0.33
    >>
    0.33
    сынын
    0.33
    POSITIVE LOGITS
     Qatar
    1.10
    Qatar
    1.09
     UAE
    1.07
     Saudi
    1.00
     Kuwait
    0.96
     Dubai
    0.93
     Emirati
    0.93
    Dubai
    0.91
     सऊदी
    0.90
     الإمارات
    0.89
    Activations Density 0.037%

    No Known Activations