© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242561
    Prev
    Next
    INDEX
    Explanations

    course descriptions

    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_40_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
     historie
    0.46
     تاريخ
    0.43
    key
    0.42
    史
    0.42
     historia
    0.41
     história
    0.41
     yazd
    0.41
     writ
    0.40
     История
    0.40
    梼
    0.39
    POSITIVE LOGITS
     courses
    0.78
     Kurs
    0.66
     Courses
    0.66
     kurs
    0.66
     cursos
    0.63
    courses
    0.61
     corso
    0.60
    Courses
    0.59
    kurs
    0.59
    Course
    0.59
    Activations Density 0.001%

    No Known Activations