Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5964
    Prev
    Next
    INDEX
    Explanations

    sentences that contain several short words and references to legal and religious matters

    oai_token-act-pair · gemini-2.0-flash

    technical terms and coding syntax

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     werd
    -0.65
    webElement
    -0.63
     nào
    -0.62
     dapat
    -0.62
     είναι
    -0.59
    terra
    -0.58
     werde
    -0.58
    RTGC
    -0.58
    서는
    -0.57
    )]=
    -0.55
    POSITIVE LOGITS
    tagHelperRunner
    0.66
    Autoritní
    0.65
     وتسجيلات
    0.62
     kasarigan
    0.59
    makeConstraints
    0.53
    SourceChecksum
    0.52
    dafx
    0.52
    __);
    0.52
    ]}{
    0.51
    ẨM
    0.50
    Activations Density 7.043%

    No Known Activations