© 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
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4634
    Prev
    Next
    INDEX
    Explanations

    a mess of words and punctuation, possibly related to dialogue.

    oai_token-act-pair · gemini-2.0-flash

    ellipsis punctuation

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

    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_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
    .");
    -1.02
    ."));
    -0.93
     */
    -0.93
    )");
    -0.89
    .")
    -0.89
    });*/
    -0.85
    .")]
    -0.84
    .”)
    -0.83
    .");
    -0.82
    >");
    -0.82
    POSITIVE LOGITS
    ...
    1.27
    …
    1.22
     ...
    1.20
     …
    1.11
    ....
    0.98
    ……
    0.96
    ….
    0.93
    .....
    0.88
    ......
    0.87
     ....
    0.84
    Activations Density 1.253%

    No Known Activations