© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10732
    Prev
    Next
    INDEX
    Explanations

    code snippets especially SQL code, potentially identifying SQL keywords, joins, and date variables.

    oai_token-act-pair · 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
    ↵
    -1.43
    ↵↵
    -1.32
    ↵↵↵
    -0.91
    .
    
    -0.72
    ,
    
    -0.68
    <eos>
    -0.65
    ;
    
    -0.64
    ↵↵↵↵
    -0.62
     
    
    -0.61
    ;
    -0.58
    POSITIVE LOGITS
    <blockquote>
    0.91
     SqlDbType
    0.77
     Mahomet
    0.76
     OGS
    0.75
     Shaksp
    0.74
     Shakspeare
    0.71
     IFT
    0.70
     PRD
    0.70
     ་་
    0.69
     Esau
    0.69
    Activations Density 12.543%

    No Known Activations