© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28654
    Prev
    Next
    INDEX
    Explanations

    crucial

    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_10_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
    i
    1.47
    n
    1.43
    o
    0.95
    it
    0.92
    e
    0.91
    a
    0.89
    u
    0.89
    s
    0.88
    ного
    0.88
    '
    0.85
    POSITIVE LOGITS
    ار
    1.07
    م
    0.97
    מ
    0.97
    ق
    0.94
    О
    0.92
    olat
    0.90
    ن
    0.89
    بد
    0.83
    рида
    0.82
    ЕТ
    0.80
    Activations Density 0.056%

    No Known Activations