© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42389
    Prev
    Next
    INDEX
    Explanations

    regulation sections

    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_22_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
     youre
    0.46
     appointed
    0.45
     বাসিন্দ
    0.45
    your
    0.43
     residente
    0.43
     jūs
    0.43
     ваш
    0.43
    ྫ
    0.42
    nYou
    0.42
    Sunglasses
    0.42
    POSITIVE LOGITS
    탭
    0.42
     tabi
    0.40
     Cabot
    0.38
    ari
    0.38
    onal
    0.38
     Constant
    0.36
    fav
    0.36
    t
    0.36
    vare
    0.36
    apon
    0.36
    Activations Density 0.001%

    No Known Activations