© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33773
    Prev
    Next
    INDEX
    Explanations

    words ending in ary or ar

    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_3_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
    f
    0.73
    寘
    0.68
    dealer
    0.68
    centos
    0.68
    ار
    0.67
    force
    0.67
    fusion
    0.67
    φέρει
    0.67
    canny
    0.67
    vasena
    0.67
    POSITIVE LOGITS
            
    0.92
                                   
    0.81
         
    0.81
                    
    0.77
                
    0.75
     н
    0.75
        
    0.74
     না
    0.74
                 
    0.72
     conosce
    0.72
    Activations Density 0.006%

    No Known Activations