© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9856
    Prev
    Next
    INDEX
    Explanations

    words related to architecture or building components

    oai_token-act-pair · gemini-2.0-flash

    window

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    -2.89
    window
    -2.56
     Window
    -2.48
     windows
    -2.47
    Window
    -2.27
     WINDOW
    -2.19
    windows
    -1.95
     ventana
    -1.83
    WINDOW
    -1.79
     fenêtre
    -1.77
    POSITIVE LOGITS
    DeleteMapping
    0.75
    #+#
    0.68
     MotionEvent
    0.63
    __":
    0.63
    addCriterion
    0.61
    enumi
    0.58
    PutMapping
    0.58
    StreetMap
    0.56
    TargetException
    0.56
    __':
    0.56
    Activations Density 5.835%

    No Known Activations