© 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. 198172
    Prev
    Next
    INDEX
    Explanations

    gate

    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
    эри
    0.45
     Sk
    0.44
     ск
    0.43
     sk
    0.41
     امنیت
    0.41
     Pneum
    0.40
     X
    0.39
     Whiskey
    0.39
    sk
    0.38
     سك
    0.38
    POSITIVE LOGITS
     gate
    0.92
     Gate
    0.83
    Gate
    0.77
     गेट
    0.67
     GATE
    0.66
    gate
    0.66
     gates
    0.65
    GATE
    0.64
    门
    0.64
    門
    0.62
    Activations Density 0.002%

    No Known Activations