© 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. 88793
    Prev
    Next
    INDEX
    Explanations

    folk society language network

    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
    ت
    1.23
    ن
    1.02
    g
    0.91
    ك
    0.89
    ing
    0.85
    т
    0.85
    n
    0.83
    н
    0.80
    nál
    0.80
    color
    0.79
    POSITIVE LOGITS
     as
    0.88
    ש
    0.75
    것
    0.67
     llamar
    0.63
    ユーザ
    0.62
     isang
    0.61
    સિ
    0.61
    다는
    0.61
    䢀
    0.61
    ’,
    0.60
    Activations Density 0.052%

    No Known Activations