© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25847
    Prev
    Next
    INDEX
    Explanations

    Indian names and conjunctives

    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_10_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
    s
    0.93
    le
    0.78
    er
    0.77
    en
    0.77
    stieg
    0.77
     an
    0.76
    es
    0.75
    pur
    0.71
     الأع
    0.69
    dire
    0.63
    POSITIVE LOGITS
    แต่
    0.85
    지만
    0.77
     tačiau
    0.76
    ن
    0.74
    телями
    0.73
    я
    0.73
    istä
    0.70
    ц
    0.70
    یت
    0.69
    一方で
    0.69
    Activations Density 0.001%

    No Known Activations