© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 1225
    Prev
    Next
    INDEX
    Explanations

    teacher

    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_44_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
     родо
    0.42
     percept
    0.40
     buck
    0.39
     Shale
    0.38
     throttling
    0.37
     ross
    0.36
     shivering
    0.36
    ቆ
    0.36
    िनी
    0.36
    sibling
    0.35
    POSITIVE LOGITS
     teacher
    1.45
    教师
    1.41
    teacher
    1.30
     öğretmen
    1.30
     teachers
    1.27
    Teacher
    1.27
    教師
    1.25
     Teacher
    1.24
    teachers
    1.23
    老师
    1.22
    Activations Density 0.129%

    No Known Activations