© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11396
    Prev
    Next
    INDEX
    Explanations

    code-related terminology, particularly involving grids, text boxes, and validation

    oai_token-act-pair · gemini-2.0-flash

    grid

    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
     grid
    -2.17
     Grid
    -2.17
    grid
    -2.16
    Grid
    -2.16
     grids
    -1.82
    grids
    -1.54
     GRID
    -1.52
    GRID
    -1.48
    GridData
    -0.87
    GridColumn
    -0.77
    POSITIVE LOGITS
     EconPapers
    0.66
    itecture
    0.61
    ynos
    0.60
     getSystem
    0.59
    fjspx
    0.58
    ellemző
    0.58
     Nij
    0.58
    HandlerContext
    0.56
    ragment
    0.55
     secret
    0.55
    Activations Density 16.804%

    No Known Activations