Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14333
    Prev
    Next
    INDEX
    Explanations

    indentation at the beginning of lines of code

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     snippetHide
    -0.81
    :+:
    -0.78
    didSet
    -0.69
     caufe
    -0.68
    rijk
    -0.67
    DockStyle
    -0.64
    homonymie
    -0.64
     nargin
    -0.63
     fhew
    -0.63
    soort
    -0.62
    POSITIVE LOGITS
       
    1.81
         
    0.75
        
    0.67
           
    0.59
          
    0.56
               
    0.51
    ! 
    0.47
     useAppContext
    0.47
                   
    0.46
      
    0.44
    Activations Density 1.369%

    No Known Activations