© 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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 3132
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to public health and opinions

    oai_token-act-pair · gemini-2.0-flash

    public opinion and health

    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
    Negative Logits
     Majefty
    -0.70
     Monfieur
    -0.61
     ſte
    -0.60
     parís
    -0.60
    especial
    -0.59
     pleaſure
    -0.59
     Parigi
    -0.58
     beſt
    -0.57
     Hift
    -0.57
     fevere
    -0.56
    POSITIVE LOGITS
    <bos>
    0.90
    ")){
    
    0.89
    __);
    0.87
    ")));
    
    0.85
    __':
    0.83
    ]:
    
    0.83
    ()]);
    0.81
    ++){
    
    0.81
    __':
    
    0.81
    "));
    
    0.80
    Activations Density 1.091%

    No Known Activations