© 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. 9711
    Prev
    Next
    INDEX
    Explanations

    the word "stroke," sometimes with a weak co-activation for words indicating comparison

    oai_token-act-pair · gemini-2.0-flash

    stroke

    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
    ↵
    -0.81
    ství
    -0.62
     \
    -0.60
     lengu
    -0.59
    ::
    -0.57
     Uang
    -0.57
    Autoritní
    -0.57
     '
    -0.56
    lė
    -0.56
    gunakan
    -0.55
    POSITIVE LOGITS
    )");
    
    1.17
    )";
    
    1.07
    ']);
    
    1.06
    '];
    
    0.96
    ]);
    
    0.93
    ');
    
    0.93
    `;
    
    0.90
    }\]
    0.89
    "])
    
    0.89
    '):
    
    0.89
    Activations Density 0.636%

    No Known Activations