© 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. 18-GEMMASCOPE-TRANSCODER-16K
    4. 6510
    Prev
    Next
    INDEX
    Explanations

    specific legal or scientific terms and their context within official agreements, procedures, or studies.

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    )";
    
    -0.88
    )");
    
    -0.81
    ]));
    
    -0.73
    setVerticalGroup
    -0.71
    )');
    -0.69
    ]))
    
    -0.67
     onCreateView
    -0.67
    }';
    -0.65
    "):
    
    -0.64
    LabelTagHelper
    -0.64
    POSITIVE LOGITS
     of
    1.34
     của
    0.90
    ของ
    0.85
     των
    0.77
     της
    0.75
    ofthe
    0.69
    RectangleBorder
    0.67
    ंदीखरीदारी
    0.63
     του
    0.62
     ofthe
    0.61
    Activations Density 2.429%

    No Known Activations