© 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. 15584
    Prev
    Next
    INDEX
    Explanations

    references or links to menus within documentation or other linked articles

    oai_token-act-pair · gemini-2.0-flash

    above

    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
     bottom
    -0.83
    below
    -0.80
     estekak
    -0.78
    bottom
    -0.78
     BOTTOM
    -0.77
     Bottom
    -0.76
     bottoms
    -0.75
     below
    -0.74
     CreateTagHelper
    -0.73
    WindowConstants
    -0.73
    POSITIVE LOGITS
     above
    1.09
     upper
    0.99
     Above
    0.97
     upstairs
    0.92
    Above
    0.92
     higher
    0.92
     up
    0.88
     Upper
    0.83
    above
    0.83
     Up
    0.82
    Activations Density 1.953%

    No Known Activations