© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1804
    Prev
    Next
    INDEX
    Explanations

    LaTeX math mode notation and mathematical symbols

    oai_token-act-pair · gemini-2.0-flash

    mathematical notation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     CreateTagHelper
    -0.74
     فريبيس
    -0.72
    tagHelperRunner
    -0.69
     ujednoznacz
    -0.68
    URLException
    -0.67
     ProtoMessage
    -0.65
     resultCode
    -0.65
    __(/*!
    -0.64
    AlterField
    -0.64
     مشين
    -0.61
    POSITIVE LOGITS
    ąt
    0.43
    TeV
    0.40
    Vertices
    0.35
     kids
    0.33
    till
    0.33
    celled
    0.33
     restaurant
    0.32
    Matrices
    0.32
     suburban
    0.32
    PERT
    0.32
    Activations Density 10.587%

    No Known Activations