© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54525
    Prev
    Next
    INDEX
    Explanations

    pragma

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    _.
    0.42
    wise
    0.41
    practical
    0.41
    demo
    0.40
    merich
    0.40
     sensibly
    0.39
    eat
    0.38
     Wise
    0.38
     ইন্ডাস্ট
    0.38
    getResult
    0.38
    POSITIVE LOGITS
    “(
    0.43
     trent
    0.41
     vero
    0.39
    <(
    0.39
     masked
    0.39
     glBindTexture
    0.39
     compi
    0.38
    “[
    0.38
    amentos
    0.37
    ATIVE
    0.37
    Activations Density 0.001%

    No Known Activations