© 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. 36138
    Prev
    Next
    INDEX
    Explanations

    countries Ukraine Sudan Taiwan

    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
    s
    0.94
    in
    0.88
    在
    0.80
    d
    0.76
    se
    0.75
    as
    0.75
    daki
    0.67
    این
    0.66
    man
    0.65
    f
    0.65
    POSITIVE LOGITS
    у
    0.75
     touted
    0.73
    ล์
    0.69
    ли
    0.66
    е
    0.65
    р
    0.64
     trajet
    0.64
    ۸
    0.63
    \%
    0.63
     be
    0.62
    Activations Density 0.009%

    No Known Activations