© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 5493
    Prev
    Next
    INDEX
    Explanations

    quotations followed by a person speaking, questions or statements followed by punctuation marks, and links for continuing to the next part of the article

    oai_token-act-pair · gemini-2.0-flash

    article previews

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     }}$}
    -1.46
    </s>
    -1.07
    </h5>
    -0.98
    </h1>
    -0.98
    ]";
    -0.88
     EnglishChoose
    -0.85
    );*/
    -0.84
    )";
    -0.84
    </u>
    -0.83
    })$}
    -0.77
    POSITIVE LOGITS
    ↵↵
    2.73
    <bos>
    0.60
     OFDb
    0.52
    ########.
    0.50
    ');
    
    0.48
    &#
    0.47
    省市镇
    0.47
    Ă
    0.44
    queryInterface
    0.44
    '];
    
    0.44
    Activations Density 2.070%

    No Known Activations