Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 2283
    Prev
    Next
    INDEX
    Explanations

    URLs and code.

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     &
    -3.64
     \&
    -2.16
    &
    -1.98
     (&
    -1.89
    (&
    -1.88
    ,&
    -1.85
    }&
    -1.77
     &\
    -1.72
    )&
    -1.67
    -&
    -1.67
    POSITIVE LOGITS
    })*/
    0.81
    });*/
    0.74
    */;
    0.63
    %";
    0.63
    };*/
    0.62
    '")
    0.61
     */;
    0.60
    }*/
    
    0.60
    。。。。
    0.59
    }*/
    0.58
    Activations Density 2.711%

    No Known Activations