© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11023
    Prev
    Next
    INDEX
    Explanations

    references to windows and windshields, especially in the context of looking out of them or cleaning them.

    oai_token-act-pair · gemini-2.0-flash

    glass and window

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     Signalez
    -0.52
     autorytatywna
    -0.50
     لينك
    -0.48
     المعيارى
    -0.47
    NameInMap
    -0.45
     medulla
    -0.45
    flich
    -0.44
    lief
    -0.44
     ویکی‌پدیا
    -0.43
     wireType
    -0.43
    POSITIVE LOGITS
     glass
    1.47
     Glass
    1.33
     window
    1.30
    Glass
    1.29
    glass
    1.27
     windows
    1.27
     GLASS
    1.20
     Window
    1.18
    Window
    1.13
    window
    1.10
    Activations Density 1.108%

    No Known Activations