© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10913
    Prev
    Next
    INDEX
    Explanations

    sentences or sentence fragments related to scientific research and studies

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    mybatisplus
    -0.76
    UnsafeEnabled
    -0.75
     ويكيميديا
    -0.70
     betweenstory
    -0.70
     సౌకర్య
    -0.69
    SPATH
    -0.69
     Wikispecies
    -0.68
    )_/¯
    -0.68
     Ribera
    -0.65
    tanleria
    -0.65
    POSITIVE LOGITS
     This
    0.59
     They
    0.58
     Those
    0.57
     Millions
    0.54
     Every
    0.53
     Its
    0.52
     Each
    0.50
     Thousands
    0.48
     Through
    0.48
    Millions
    0.46
    Activations Density 1.912%

    No Known Activations