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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 2520
    Prev
    Next
    INDEX
    Explanations

    words that frequently occur near HTML tags, especially tags related to links and lists

    oai_token-act-pair · gemini-2.0-flash

    closing HTML tags

    np_token-act-pair-logits · gpt-4o-mini

    HTML tags

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ↵↵
    -1.38
    <eos>
    -1.05
    \\
    -0.56
    Chham
    -0.55
     Wikiseite
    -0.53
    <h3>
    -0.53
    <b>
    -0.52
     JADX
    -0.48
    GEBURTS
    -0.48
     wikipagina
    -0.48
    POSITIVE LOGITS
    </strong>
    2.63
    </u>
    2.28
    </em>
    2.23
    </b>
    2.09
    </h2>
    1.96
    )$}
    1.94
    </h4>
    1.94
    </h5>
    1.86
    </code>
    1.82
    </h3>
    1.80
    Activations Density 29.577%

    No Known Activations