© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10751
    Prev
    Next
    INDEX
    Explanations

    words referring to physical objects/suits of armor and the state of being

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    featureID
    -0.60
     with
    -0.59
     initComponents
    -0.58
     With
    -0.54
    DeleteBehavior
    -0.50
     avec
    -0.50
    with
    -0.49
     ProtoMessage
    -0.48
    出版年
    -0.47
    exitRule
    -0.47
    POSITIVE LOGITS
     surla
    0.66
    utilisons
    0.65
     AssemblyProduct
    0.62
     ModelAndView
    0.60
    AsUp
    0.60
     BoxFit
    0.58
    prised
    0.58
    CodeAttribute
    0.58
     inca
    0.57
     Skor
    0.56
    Activations Density 1.847%

    No Known Activations