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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6669
    Prev
    Next
    INDEX
    Explanations

    whitespace between math symbols

    oai_token-act-pair · gemini-2.0-flash

    mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
      
    -1.22
        
    -1.06
     "
    -0.88
            
    -0.83
         
    -0.82
          
    -0.82
    -0.80
     I
    -0.79
     the
    -0.79
       
    -0.78
    POSITIVE LOGITS
     Efq
    1.65
     pleaſure
    1.53
     Majefty
    1.53
     myſelf
    1.48
     Jefus
    1.47
     houſe
    1.47
     purpoſe
    1.45
     Anſ
    1.45
     greateſt
    1.43
     Houſe
    1.41
    Activations Density 0.847%

    No Known Activations