© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2813
    Prev
    Next
    INDEX
    Explanations

    mentions of physical damage to property or features of buildings, including windows and lights

    oai_token-act-pair · gemini-2.0-flash

    Windows

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    -1.63
    window
    -1.41
     Window
    -1.24
    Window
    -1.09
     WINDOW
    -1.07
     fenêtre
    -1.03
     ventana
    -0.91
    窗口
    -0.88
    WINDOW
    -0.86
     janela
    -0.86
    POSITIVE LOGITS
    Windows
    0.81
     Windows
    0.77
    windows
    0.65
     WINDOWS
    0.64
    WINDOWS
    0.61
    __*/
    0.57
    __(/*!
    0.56
    Espèce
    0.54
    Win
    0.52
     win
    0.52
    Activations Density 3.962%

    No Known Activations