© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8531
    Prev
    Next
    INDEX
    Explanations

    variables related to boxes in code

    oai_token-act-pair · gemini-2.0-flash

    box

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     box
    -3.16
    box
    -2.95
     Box
    -2.91
    Box
    -2.84
     boxes
    -2.69
     BOX
    -2.63
    BOX
    -2.61
    boxes
    -2.61
     Boxes
    -2.47
    Boxes
    -2.22
    POSITIVE LOGITS
    Einzelnachweise
    0.64
    mtable
    0.52
     ujednoznacz
    0.49
     volna
    0.49
    fitriones
    0.49
    linspace
    0.48
    WebServlet
    0.47
     abs
    0.47
    əsi
    0.46
    ospor
    0.46
    Activations Density 0.317%

    No Known Activations