© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1875
    Prev
    Next
    INDEX
    Explanations

    classroom and class

    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
    LPTMR
    0.39
     सक्छ
    0.38
    蒽
    0.38
     देसी
    0.36
    (',',
    0.36
    
    0.36
     Kiv
    0.36
    오
    0.36
     sosp
    0.35
     evolução
    0.35
    POSITIVE LOGITS
     classroom
    1.24
    classroom
    1.12
     className
    1.09
     Classroom
    1.08
    className
    0.96
     classrooms
    0.95
    教室
    0.90
     clas
    0.86
    classname
    0.83
     class
    0.82
    Activations Density 0.095%

    No Known Activations