© 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. 33728
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     със
    0.49
     with
    0.48
    लाई
    0.40
    roč
    0.40
    에는
    0.40
     với
    0.39
    徉
    0.39
     With
    0.39
     gyda
    0.39
    .",
    0.38
    POSITIVE LOGITS
     tôi
    0.46
    我的
    0.44
    我是
    0.40
    Heavy
    0.40
    ผม
    0.39
    विड़
    0.39
    greet
    0.38
    >′</
    0.37
    Mixin
    0.37
    jeg
    0.37
    Activations Density 0.091%

    No Known Activations