© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9088
    Prev
    Next
    INDEX
    Explanations

    code related to the manipulation of indexed data structures, particularly within a charting or layout context

    oai_token-act-pair · gemini-2.0-flash

    index, position

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ValueStyle
    -1.02
    TagMode
    -0.94
     مشين
    -0.93
    DockStyle
    -0.92
    MemoryWarning
    -0.91
     שוליים
    -0.91
    NameInMap
    -0.89
    CloseOperation
    -0.87
     المعيارى
    -0.86
    AccessorTable
    -0.85
    POSITIVE LOGITS
     then
    0.48
     still
    0.42
    GLFW
    0.40
     daardoor
    0.38
    登上
    0.36
     seguito
    0.35
    Reducers
    0.35
    нта
    0.34
     ran
    0.34
     step
    0.34
    Activations Density 2.085%

    No Known Activations