© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 166683
    Prev
    Next
    INDEX
    Explanations

    instructor or classroom

    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_56_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
     수
    0.81
    수
    0.71
    수에
    0.50
    수의
    0.47
     thu
    0.43
    수를
    0.42
    収
    0.42
    수한
    0.40
    收
    0.40
     Sud
    0.40
    POSITIVE LOGITS
     instructor
    1.63
     Instructor
    1.59
    Instructor
    1.55
    instructor
    1.51
     Classroom
    1.18
     classroom
    1.17
    classroom
    1.17
     instructors
    1.10
    学员
    0.93
     cadet
    0.87
    Activations Density 0.001%

    No Known Activations