© 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. 34799
    Prev
    Next
    INDEX
    Explanations

    suffix less

    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
    et
    1.05
    ه
    1.02
    া
    0.90
    t
    0.86
    a
    0.85
    0
    0.84
    o
    0.81
    in
    0.80
    ا
    0.77
    aing
    0.73
    POSITIVE LOGITS
    ма
    0.88
    е
    0.73
    પ
    0.72
    у
    0.72
    л
    0.71
    F
    0.70
    ле
    0.70
    L
    0.70
     (
    0.69
     a
    0.67
    Activations Density 0.019%

    No Known Activations