© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84959
    Prev
    Next
    INDEX
    Explanations

    Economics Nobel Prize

    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_23_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
     kennt
    0.20
    🌭
    0.17
     daylight
    0.17
     näher
    0.16
     feather
    0.16
     enthält
    0.16
    晗
    0.16
     😘
    0.16
     localidades
    0.16
     cerca
    0.16
    POSITIVE LOGITS
               
    0.16
              
    0.15
             
    0.15
    _{
    0.15
    epend
    0.15
           
    0.14
          
    0.14
    np
    0.14
    First
    0.14
    añ
    0.14
    Activations Density 0.001%

    No Known Activations