© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 10684
    Prev
    Next
    INDEX
    Explanations

    the word "expansion" and also words that mean to get bigger, or larger scale

    oai_token-act-pair · gemini-2.0-flash

    expansion

    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
    ,
    -0.66
     and
    -0.53
    -
    -0.50
     отношение
    -0.50
     or
    -0.49
     Abp
    -0.48
    e
    -0.48
     pairs
    -0.47
     in
    -0.47
     таки
    -0.47
    POSITIVE LOGITS
     Theſe
    1.19
    )");
    
    1.11
    $")
    1.09
    "){
    
    1.08
     ―――――
    1.05
    )";
    
    1.05
    "),
    
    1.04
     ")
    
    1.03
    '));
    
    1.03
    mybatisplus
    1.02
    Activations Density 1.367%

    No Known Activations