© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 176065
    Prev
    Next
    INDEX
    Explanations

    grades OR junior

    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
     classmate
    0.42
    <unused47>
    0.40
     ক্লাশ
    0.40
     clichés
    0.40
    ́p
    0.39
    inschaft
    0.38
     classmates
    0.38
    ırım
    0.37
     klas
    0.37
    <unused45>
    0.37
    POSITIVE LOGITS
     Grade
    0.80
    Grade
    0.75
     grade
    0.73
     GRADE
    0.72
    GRADE
    0.70
    grade
    0.64
     Grades
    0.61
     junior
    0.57
     Junior
    0.55
     grades
    0.52
    Activations Density 0.001%

    No Known Activations