© 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. 8528
    Prev
    Next
    INDEX
    Explanations

    text from legal historical documents, including names and citations of sources

    oai_token-act-pair · gemini-2.0-flash

    non-English language references or citations

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

    Legal and historical texts

    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
    IBOutlet
    -0.55
     deepest
    -0.54
     deep
    -0.48
    Espèce
    -0.47
     respec
    -0.43
    vation
    -0.43
    mä
    -0.43
    deh
    -0.41
    deep
    -0.41
     deeper
    -0.41
    POSITIVE LOGITS
    脚注の使い方
    0.97
     Référence
    0.79
    expandindo
    0.78
    Hentet
    0.76
     فريبيس
    0.71
    رشف
    0.71
     AssemblyTitle
    0.69
     ostavi
    0.66
    Зноскі
    0.65
     utafitiHapana
    0.65
    Activations Density 1.408%

    No Known Activations