© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 156586
    Prev
    Next
    INDEX
    Explanations

    supervision oversight

    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_50_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
     sustent
    0.37
    ularity
    0.37
    btnClose
    0.36
     sosten
    0.35
     Wilhel
    0.35
    @[+][
    0.34
    ikala
    0.34
     SSH
    0.34
    ))){
    0.34
     Yuki
    0.34
    POSITIVE LOGITS
     supervision
    1.80
    監督
    1.70
     Supervision
    1.66
     supervis
    1.60
    监督
    1.57
     supervising
    1.55
     감독
    1.53
     supervise
    1.52
     oversight
    1.48
     supervisory
    1.45
    Activations Density 0.001%

    No Known Activations