© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 168715
    Prev
    Next
    INDEX
    Explanations

    numbers and geographical data

    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_34_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     sortie
    0.36
    ScheduledAction
    0.34
    aty
    0.33
     reformation
    0.33
    etrain
    0.32
     bowtie
    0.32
     ক্যাপ্টেন
    0.31
    峻
    0.31
     captain
    0.31
    コート
    0.31
    POSITIVE LOGITS
    हित्य
    0.32
    
    0.30
    Presented
    0.30
    erek
    0.30
     harmonize
    0.30
    Merging
    0.29
     فا
    0.29
    Thought
    0.29
    roller
    0.29
     প্রবাসী
    0.29
    Activations Density 0.001%

    No Known Activations