© 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. 3229
    Prev
    Next
    INDEX
    Explanations

    LaTeX math notation, especially fractions, gammas, and deltas

    oai_token-act-pair · gemini-2.0-flash

    say "}{"

    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
    <h2>
    -0.58
    },
    -0.56
    }>
    -0.56
    }=
    -0.50
    Demografia
    -0.49
    };
    -0.46
     assigns
    -0.44
    ],
    -0.44
    voie
    -0.43
    ItemBackground
    -0.43
    POSITIVE LOGITS
    </em>
    1.55
    </i>
    1.48
    ();*/
    1.13
    </h6>
    1.10
     */
    
    1.03
    >*/
    1.01
    </h5>
    0.97
    ;*/
    0.96
    </h3>
    0.94
    );*/
    0.93
    Activations Density 2.539%

    No Known Activations