© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 92189
    Prev
    Next
    INDEX
    Explanations

    record

    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_60_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
    class
    0.57
     Class
    0.50
    classes
    0.49
     class
    0.48
     Classes
    0.47
    */
    0.46
    -*/
    0.44
    
    0.44
    
    0.43
    techn
    0.43
    POSITIVE LOGITS
     record
    2.31
    Record
    1.99
     Record
    1.94
    record
    1.85
     RECORD
    1.59
     रिकॉर्ड
    1.52
    RECORD
    1.48
    记录
    1.43
     রেকর্ড
    1.39
     рекорд
    1.39
    Activations Density 0.000%

    No Known Activations