© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 16020
    Prev
    Next
    INDEX
    Explanations

    the word "sacrifice"

    oai_token-act-pair · gemini-2.0-flash

    sacrifice

    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
    .";
    
    -1.03
    '},
    
    -1.01
    `;
    
    -0.98
    ='';
    
    -0.95
     tartalomajánló
    -0.95
    )");
    
    -0.95
    )";
    
    -0.94
    `,
    
    -0.93
    "];
    
    -0.92
    "]];
    -0.92
    POSITIVE LOGITS
     the
    0.90
    ,
    0.78
     a
    0.68
    <bos>
    0.59
     for
    0.58
    :
    0.57
     its
    0.54
    -
    0.54
     it
    0.51
    f
    0.49
    Activations Density 0.667%

    No Known Activations