© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124580
    Prev
    Next
    INDEX
    Explanations

    names like Biel, Bell, Drew

    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_3_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
    obat
    0.57
    あり
    0.57
    国の
    0.57
    glycos
    0.57
     দিয়ে
    0.55
    ತ್
    0.55
    )^{*}\
    0.55
    1
    0.55
     یا
    0.54
     tua
    0.54
    POSITIVE LOGITS
    ن
    0.98
    ه
    0.91
    ン
    0.89
    هم
    0.85
    a
    0.85
    بي
    0.83
    ي
    0.81
    न
    0.80
    ان
    0.79
    ম
    0.79
    Activations Density 0.000%

    No Known Activations