© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210184
    Prev
    Next
    INDEX
    Explanations

    pixel, app, Pixlr, Piskel

    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_5_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
    u
    1.68
    i
    1.05
    k
    1.00
    uoj
    0.97
    y
    0.97
     scherm
    0.88
    ጋገብ
    0.86
     Ги
    0.85
    torch
    0.84
     Чар
    0.83
    POSITIVE LOGITS
    ال
    1.44
    أ
    1.29
    ار
    1.28
    מ
    1.26
    م
    1.19
    ня
    1.13
    ม
    1.11
    த
    1.10
    ड
    1.10
     an
    1.09
    Activations Density 0.000%

    No Known Activations