© 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. 40065
    Prev
    Next
    INDEX
    Explanations

    snail mucin, hydrating skin, Hydrogen Peroxide

    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
     сем
    0.57
    /
    0.52
    عرف
    0.50
     modos
    0.50
    起
    0.50
    ﻐ
    0.48
     که
    0.48
     ceremonies
    0.47
     {
    0.47
     représentent
    0.47
    POSITIVE LOGITS
    ut
    0.63
    utama
    0.52
     cellulite
    0.50
    ok
    0.48
     handbag
    0.48
     vegetable
    0.46
     Einen
    0.46
    kyat
    0.46
    cort
    0.45
    filtered
    0.45
    Activations Density 0.024%

    No Known Activations