© 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. 10755
    Prev
    Next
    INDEX
    Explanations

    phrases featuring the word "to" followed by a verb

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · 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
    glBegin
    -0.56
    رأة
    -0.46
    kite
    -0.46
    深的
    -0.44
    penta
    -0.44
     précise
    -0.44
     jsonArray
    -0.44
     debole
    -0.44
    ட்ச
    -0.44
    bruck
    -0.43
    POSITIVE LOGITS
    ValueStyle
    0.77
     nahilalakip
    0.76
    setVerticalGroup
    0.71
     Wicidata
    0.70
    AddTagHelper
    0.69
    PerformLayout
    0.66
    BagConstraints
    0.65
    Tikang
    0.64
    UnsafeEnabled
    0.64
    ViewFeatures
    0.60
    Activations Density 2.088%

    No Known Activations