© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12527
    Prev
    Next
    INDEX
    Explanations

    words related to the shipping industry, especially registers, ships, and cargo

    oai_token-act-pair · gemini-2.0-flash

    gates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     שוליים
    -0.58
     EconPapers
    -0.57
     Reverso
    -0.52
    makeConstraints
    -0.49
    ergies
    -0.49
    __((
    -0.48
    webElement
    -0.47
    
    -0.47
    deals
    -0.47
    styleType
    -0.46
    POSITIVE LOGITS
     ships
    0.88
     yacht
    0.77
     yachts
    0.75
    boats
    0.74
    boat
    0.73
     boats
    0.73
     ship
    0.73
     warships
    0.71
     Ships
    0.71
    ship
    0.70
    Activations Density 0.694%

    No Known Activations