© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12504
    Prev
    Next
    INDEX
    Explanations

    words related to science and research

    oai_token-act-pair · gemini-2.0-flash

    models

    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
     held
    -0.95
    held
    -0.87
     HELD
    -0.85
    aarrggbb
    -0.85
     Held
    -0.77
    Held
    -0.73
    hold
    -0.70
    tagHelperRunner
    -0.68
    oredCriteria
    -0.67
    utilisons
    -0.66
    POSITIVE LOGITS
     model
    0.61
     models
    0.54
    モデル
    0.47
    modellen
    0.46
     M
    0.45
    model
    0.45
    <table>
    0.45
    Models
    0.44
    models
    0.44
     modelos
    0.44
    Activations Density 0.966%

    No Known Activations