© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 149134
    Prev
    Next
    INDEX
    Explanations

    Halfling

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    lashes
    0.45
    u
    0.41
     बीच
    0.38
    tı
    0.38
    ве
    0.38
     Learners
    0.37
     वातावर
    0.37
     Lernen
    0.35
    تين
    0.35
    る
    0.35
    POSITIVE LOGITS
                   
    0.46
                       
    0.45
                      
    0.42
                                  
    0.41
    alada
    0.41
                     
    0.41
                                 
    0.40
                  
    0.39
    ()`
    0.39
    inus
    0.39
    Activations Density 0.000%

    No Known Activations