© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 16699
    Prev
    Next
    INDEX
    Explanations

    improvement and betterment

    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
    Not in Any Lists

    No Comments

    Negative Logits
    }]\
    0.40
    ]}{
    0.37
    }}}\
    0.36
    Pend
    0.36
    lanelet
    0.35
    Anglo
    0.34
    
    0.34
    鹌
    0.34
     مكت
    0.33
     ఆధ్యా
    0.33
    POSITIVE LOGITS
     improvement
    1.13
     улучшения
    1.00
     improving
    1.00
     Improvement
    1.00
     verbeter
    0.99
    改善
    0.99
     mejora
    0.98
     mejorar
    0.97
     улуч
    0.96
    improvement
    0.95
    Activations Density 0.094%

    No Known Activations