© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9579
    Prev
    Next
    INDEX
    Explanations

    words that refer to glass used in buildings and vehicles

    oai_token-act-pair · gemini-2.0-flash

    glass

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     window
    -0.97
     Window
    -0.91
    Window
    -0.85
    window
    -0.83
     windows
    -0.82
     Fenster
    -0.82
     WINDOW
    -0.81
     glass
    -0.75
    窗口
    -0.75
     fenêtre
    -0.74
    POSITIVE LOGITS
     nakalista
    0.48
    enschaft
    0.48
    Quack
    0.48
    inaldi
    0.45
     net
    0.45
     Votes
    0.44
    getMenuInflater
    0.43
    ExecuteReader
    0.42
     saisi
    0.41
     podjela
    0.41
    Activations Density 20.087%

    No Known Activations