© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 15597
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people, and also words surrounding it.

    oai_token-act-pair · gemini-2.0-flash

    connections

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    makeConstraints
    -0.84
    principalColumn
    -0.81
    
    -0.80
    发表于
    -0.71
    AndEndTag
    -0.69
    posedge
    -0.67
    IsContent
    -0.63
    LLocation
    -0.60
     Gass
    -0.59
    awtextra
    -0.57
    POSITIVE LOGITS
     connected
    0.93
    connected
    0.77
     connection
    0.77
    Connected
    0.73
     linked
    0.73
     connect
    0.73
     introduced
    0.69
     Connected
    0.69
    Introdu
    0.69
    connection
    0.69
    Activations Density 3.982%

    No Known Activations