© 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. 11734
    Prev
    Next
    INDEX
    Explanations

    words and symbols related to experimental results and mathematical significance

    oai_token-act-pair · gemini-2.0-flash

    significant

    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
     nakalista
    -1.05
    setVerticalGroup
    -1.03
    RenderAtEndOf
    -0.92
    WithIOException
    -0.88
     otomatig
    -0.78
     defaultstate
    -0.74
     EconPapers
    -0.73
     propOrder
    -0.72
     متعلقه
    -0.71
    Rujuakan
    -0.71
    POSITIVE LOGITS
     significant
    1.57
     significantly
    1.52
    significant
    1.44
     Significant
    1.38
    Significant
    1.36
    significantly
    1.30
     Significantly
    1.26
     SIGNIFIC
    1.24
     statistically
    1.15
     signific
    1.11
    Activations Density 5.609%

    No Known Activations