© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39415
    Prev
    Next
    INDEX
    Explanations

    glass, fiber, frame, layers, white

    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
    Glare
    0.57
     polyhedron
    0.56
    Xaml
    0.54
    Glass
    0.54
     cinética
    0.52
    釉
    0.52
    玻璃
    0.51
    玻
    0.51
    Okno
    0.50
     유리
    0.50
    POSITIVE LOGITS
    al
    0.64
    os
    0.62
    aj
    0.62
    ul
    0.60
    er
    0.58
    uj
    0.57
    unes
    0.56
    l
    0.55
    il
    0.54
    ut
    0.54
    Activations Density 0.023%

    No Known Activations