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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 205847
    Prev
    Next
    INDEX
    Explanations

    foreign characters

    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_46_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
     rifle
    0.41
     chai
    0.40
    索
    0.40
     Sora
    0.39
    ুতি
    0.38
     sõ
    0.38
     curious
    0.38
    腮
    0.38
     পরিসংখ্যান
    0.37
    瓶
    0.37
    POSITIVE LOGITS
    ඳ
    0.39
     कार्यकारी
    0.37
    दायक
    0.36
    ෆ
    0.34
     মাননীয়
    0.33
     仮
    0.33
     работа
    0.33
     Fehler
    0.33
    ueroa
    0.33
    ෂ
    0.33
    Activations Density 0.000%

    No Known Activations