© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14253
    Prev
    Next
    INDEX
    Explanations

    words and phrases common in formal writing, news articles, and medical articles (e.g., dates, locations, reports).

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    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
    </strong>
    -1.54
    </em>
    -1.40
    </b>
    -1.30
    </u>
    -1.19
    </i>
    -1.18
    </code>
    -0.96
    </s>
    -0.90
    </sub>
    -0.84
    </h4>
    -0.82
    </sup>
    -0.82
    POSITIVE LOGITS
    \\
    1.14
    -\\
    1.09
    ,\\
    1.02
    ;\\
    1.02
     $\$
    1.01
     $\&$
    0.97
    .\\
    0.96
    ?\\
    0.96
     \_
    0.94
    $\\
    0.92
    Activations Density 59.387%

    No Known Activations