© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14842
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms, especially those related to medical or scientific fields

    oai_token-act-pair · gemini-2.0-flash

    G

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
      
    -0.55
                                   
    -0.55
    …
    -0.54
    <strong>
    -0.53
                              
    -0.52
     The
    -0.50
    <h2>
    -0.50
        
    -0.49
    ↵
    -0.49
                  
    -0.49
    POSITIVE LOGITS
     للاسماء
    0.69
     createState
    0.68
     avoient
    0.59
    FTFY
    0.59
     feroit
    0.57
     étoient
    0.56
    IntoConstraints
    0.56
     initComponents
    0.55
     intptr
    0.55
     FetchType
    0.55
    Activations Density 51.521%

    No Known Activations