© 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. 9312
    Prev
    Next
    INDEX
    Explanations

    parentheses, especially empty parentheses or those involved in function calls

    oai_token-act-pair · gemini-2.0-flash

    parentheses

    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
    }));
    -0.86
    DoubleQuotes
    -0.85
    )));
    -0.81
    );
    -0.81
    ];
    -0.77
    }]);
    -0.76
    ());
    -0.75
    ");
    -0.75
    </th>
    -0.74
    "])
    -0.74
    POSITIVE LOGITS
    <bos>
    1.63
     raiſ
    0.97
     itſelf
    0.91
     pleaſure
    0.87
     ſever
    0.85
     Shakspeare
    0.83
     ARXIV
    0.83
     faſt
    0.82
     Efq
    0.80
     myſelf
    0.79
    Activations Density 1.363%

    No Known Activations