© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 1828
    Prev
    Next
    INDEX
    Explanations

    strings of text that might be computer code

    oai_token-act-pair · gemini-2.0-flash

    programming syntax elements (like parentheses and quotes)

    np_token-act-pair-logits · gpt-4o-mini

    Parenthesis and quotes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     EdgeInsets
    -0.80
    /,
    -0.65
    </>
    -0.63
    gnore
    -0.60
    /.
    -0.60
     ويكيميديا
    -0.59
    //});
    -0.57
    -.
    -0.57
    MENAFN
    -0.57
    -,
    -0.55
    POSITIVE LOGITS
    )");
    
    0.73
    "):
    
    0.71
    ".
    
    0.68
    )]
    
    0.68
    '))
    
    0.66
    "))
    
    0.65
    ")]
    
    0.65
    !")
    
    0.65
    )";
    
    0.65
    "];
    
    0.64
    Activations Density 1.598%

    No Known Activations