© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87625
    Prev
    Next
    INDEX
    Explanations

    IP phone, cameras, passthrough

    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
     be
    0.77
     an
    0.68
    J
    0.64
    e
    0.63
    是因为
    0.63
    ו
    0.63
    ser
    0.62
    就是
    0.62
    多的
    0.61
    et
    0.57
    POSITIVE LOGITS
    رین
    0.71
    влека
    0.70
    он
    0.69
    ке
    0.69
     CLL
    0.69
     Gigi
    0.68
    га
    0.68
    ﻌ
    0.68
    śla
    0.67
    वालों
    0.67
    Activations Density 0.001%

    No Known Activations