© 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. 43367
    Prev
    Next
    INDEX
    Explanations

    Matthew Arnold, Correlation

    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
     is
    0.99
    ed
    0.76
    a
    0.73
    e
    0.72
    šću
    0.71
    in
    0.71
    ма
    0.68
    à
    0.68
     trainer
    0.67
    ̀m
    0.66
    POSITIVE LOGITS
    I
    0.70
    ্রো
    0.64
    "]')
    0.64
    shims
    0.60
    われる
    0.59
    ?",
    0.59
     Володи
    0.58
     Кали
    0.57
     ?",
    0.57
    w
    0.57
    Activations Density 0.001%

    No Known Activations