© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126175
    Prev
    Next
    INDEX
    Explanations

    Janssen vaccine, Joslin Diabetes

    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
    on
    0.91
     on
    0.89
    as
    0.88
    ens
    0.73
    at
    0.73
    int
    0.72
    ü
    0.72
    ار
    0.71
    리
    0.71
    ne
    0.71
    POSITIVE LOGITS
    ﻛ
    0.67
    <unused444>
    0.63
     ﺍﻟ
    0.63
     terraz
    0.62
     まず
    0.61
     nhàng
    0.61
    ﻓ
    0.61
    >(</
    0.60
     एनसीईआरटी
    0.60
    a
    0.59
    Activations Density 0.000%

    No Known Activations