© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6030
    Prev
    Next
    INDEX
    Explanations

    descriptions of looking out a window

    oai_token-act-pair · gemini-2.0-flash

    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_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    </thead>
    -0.48
    يكب
    -0.48
    esModule
    -0.45
    EndInit
    -0.45
    ApiModel
    -0.44
    DOCTYPE
    -0.43
     unknownFields
    -0.43
    ogia
    -0.43
    Aholisi
    -0.42
    serve
    -0.42
    POSITIVE LOGITS
     windows
    1.91
     window
    1.88
     Window
    1.77
    window
    1.63
    Window
    1.59
    windows
    1.56
     WINDOW
    1.55
     WINDOWS
    1.49
     Windows
    1.46
     janela
    1.46
    Activations Density 0.535%

    No Known Activations