© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21605
    Prev
    Next
    INDEX
    Explanations

    ligatures and French

    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_56_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
     Kha
    0.42
    㘟
    0.39
    %$$
    0.38
    喿
    0.38
     ايا
    0.38
     bhikkhave
    0.37
     স্বদেশ
    0.36
    зне
    0.35
    ंगाना
    0.35
    dades
    0.35
    POSITIVE LOGITS
     æ
    0.82
     Ã
    0.79
    Æ
    0.79
    œ
    0.77
    æ
    0.76
     œ
    0.74
    Ã
    0.70
    ӕ
    0.67
     Æ
    0.67
    ¾
    0.64
    Activations Density 0.002%

    No Known Activations