© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260340
    Prev
    Next
    INDEX
    Explanations

    double taxation or hyperloop

    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_22_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
    stvu
    0.53
     resear
    0.49
     চক্ষে
    0.48
     京
    0.48
     Ethics
    0.47
    स्व
    0.46
    Ethics
    0.45
    ার্ড
    0.45
     পরিপ্রে
    0.45
    ंडर
    0.45
    POSITIVE LOGITS
     সিল
    0.46
    ín
    0.45
     Maschine
    0.45
    ↵↵
    0.43
    ですので
    0.42
     intrepid
    0.42
     lup
    0.41
     defiant
    0.41
     pinnacle
    0.41
    วาง
    0.40
    Activations Density 0.000%

    No Known Activations