© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 177813
    Prev
    Next
    INDEX
    Explanations

    user or path names

    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_29_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
    部屋
    0.31
     shaving
    0.28
    小
    0.28
     состав
    0.28
    保育
    0.27
     ________
    0.27
    
    0.27
    ஷா
    0.26
     shutil
    0.26
     ಸಾಕಷ್ಟು
    0.26
    POSITIVE LOGITS
    njih
    0.35
     więc
    0.33
     الرخصة
    0.32
    व्यव
    0.32
     அவர்களுடைய
    0.32
     deras
    0.32
    łat
    0.31
     фізи
    0.31
     leurs
    0.31
     এক্সপ্রেস
    0.30
    Activations Density 0.009%

    No Known Activations