© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15410
    Prev
    Next
    INDEX
    Explanations

    words related to amounts or units

    oai_token-act-pair · gemini-2.0-flash

    legal or official situations

    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
     mga
    -0.60
    vels
    -0.54
    ites
    -0.54
     those
    -0.50
     cu
    -0.49
     these
    -0.48
    bitur
    -0.47
    hems
    -0.47
    ılar
    -0.46
     pels
    -0.46
    POSITIVE LOGITS
    titleMargin
    0.84
     EClass
    0.83
     âmes
    0.75
     ComVisible
    0.75
    setVerticalGroup
    0.75
    AddTagHelper
    0.75
    تقاوى
    0.74
     <=",
    0.74
     resourceCulture
    0.73
     flesta
    0.73
    Activations Density 3.026%

    No Known Activations