© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14946
    Prev
    Next
    INDEX
    Explanations

    export variablesadjusts

    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_13_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
    𝗹
    0.68
    ర్
    0.57
    hydrox
    0.52
    c
    0.52
    ల్
    0.51
    ланд
    0.51
    ِل
    0.49
    ол
    0.49
    活動
    0.48
    舝
    0.48
    POSITIVE LOGITS
         
    0.55
    ’,
    0.54
    ↵↵↵
    0.53
          
    0.53
        
    0.52
    ↵↵↵↵
    0.51
     dụng
    0.51
    ↵↵↵↵↵
    0.50
     ஏற்று
    0.50
    ↵↵↵↵↵↵↵
    0.50
    Activations Density 0.078%

    No Known Activations