© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33699
    Prev
    Next
    INDEX
    Explanations

    At

    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
    smallest
    0.69
     smallest
    0.68
     най
    0.63
    最
    0.62
     सबसे
    0.61
     가장
    0.59
    最小
    0.57
    Smaller
    0.57
     lowest
    0.57
     menores
    0.56
    POSITIVE LOGITS
    agge
    0.42
     Esse
    0.39
    ნი
    0.38
     pathological
    0.38
    ینڈ
    0.38
    ynthetic
    0.38
    ەر
    0.38
    reo
    0.38
    哒
    0.37
     فول
    0.37
    Activations Density 0.003%

    No Known Activations