© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60143
    Prev
    Next
    INDEX
    Explanations

    CIELAB, RGB, HSL color spaces

    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_11_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
    o
    0.33
    ADOW
    0.29
    iski
    0.29
     oars
    0.27
    U
    0.26
    eg
    0.26
    ik
    0.25
    I
    0.25
    ALE
    0.25
     Covers
    0.25
    POSITIVE LOGITS
    म
    0.34
    מ
    0.32
    гле
    0.29
     implicitly
    0.29
    ม
    0.29
     protéines
    0.28
     timeless
    0.27
    ódio
    0.27
     glamour
    0.27
    гим
    0.27
    Activations Density 0.009%

    No Known Activations