© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82637
    Prev
    Next
    INDEX
    Explanations

    multipart/form-data

    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_0_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
    in
    2.77
    t
    1.93
    um
    1.83
    un
    1.73
    ar
    1.66
    it
    1.52
    as
    1.52
    í
    1.51
    i
    1.48
    o
    1.42
    POSITIVE LOGITS
    মনসিংহ
    1.20
    스가
    1.12
    前記
    1.12
     فإن
    1.11
    ни
    1.09
    ných
    1.09
    )，
    1.09
    kého
    1.08
     سي
    1.07
    स्पद
    1.05
    Activations Density 0.000%

    No Known Activations