© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16569
    Prev
    Next
    INDEX
    Explanations

    import path components

    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_15_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
     Karaoke
    0.57
     l
    0.55
     взять
    0.52
     возь
    0.51
    u
    0.51
     +
    0.48
    irs
    0.48
    ful
    0.48
    štění
    0.48
      
    0.47
    POSITIVE LOGITS
    ◢
    0.54
     cityName
    0.49
    是你
    0.48
    localized
    0.47
    選擇
    0.46
     ඔබේ
    0.46
    नए
    0.45
    new
    0.45
    新的
    0.45
     нового
    0.45
    Activations Density 0.000%

    No Known Activations