© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 31616
    Prev
    Next
    INDEX
    Explanations

    pretrained from_pretrained

    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_7_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
    에서는
    0.69
    에
    0.68
    ﻟ
    0.68
    -
    0.66
    ﻣ
    0.66
    人气
    0.63
    에는
    0.61
     ಇನ್ನ
    0.57
    ких
    0.57
    ).
    0.57
    POSITIVE LOGITS
    ר
    0.92
    v
    0.91
    ut
    0.84
    ar
    0.81
    ap
    0.80
    et
    0.78
    b
    0.78
    el
    0.77
    ur
    0.76
    in
    0.73
    Activations Density 0.001%

    No Known Activations