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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11305
    Prev
    Next
    INDEX
    Explanations

    the word "in" followed by a number

    oai_token-act-pair · gemini-2.0-flash

    particles and conjunctions in descriptions

    np_token-act-pair-logits · gpt-4o-mini
    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
    />";
    -0.63
    >",
    -0.62
     />";
    -0.59
     />);
    -0.57
    ]";
    -0.56
     ModelExpression
    -0.55
    )");
    -0.55
    '));
    -0.54
    `;
    -0.54
    Then
    -0.54
    POSITIVE LOGITS
     those
    0.60
     réparation
    0.53
    qrstuvwxyz
    0.52
    viding
    0.51
    toft
    0.51
    liski
    0.50
    Those
    0.50
     Those
    0.49
     THOSE
    0.48
    ENBERG
    0.48
    Activations Density 1.078%

    No Known Activations