© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16505
    Prev
    Next
    INDEX
    Explanations

    ab

    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_15_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
     Información
    0.63
    <unused1083>
    0.62
     வைர
    0.59
     тях
    0.59
    <unused1832>
    0.59
    <unused1047>
    0.58
     ihrem
    0.58
    <unused374>
    0.58
    <unused510>
    0.58
    <unused384>
    0.57
    POSITIVE LOGITS
        
    0.84
                    
    0.60
       
    0.58
    ，
    0.58
     repeats
    0.57
      
    0.56
    My
    0.56
            
    0.55
          
    0.55
    '
    0.54
    Activations Density 0.002%

    No Known Activations