© 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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5261
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols within a document

    oai_token-act-pair · gemini-2.0-flash

    technical notation and mathematical symbols

    np_token-act-pair-logits · gpt-4o-mini

    $

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     ${\
    -0.68
     $\
    -0.67
     ${
    -0.64
     ()
    -0.63
     Soto
    -0.59
     ,
    -0.57
     Mix
    -0.56
    )$_
    -0.56
     $_
    -0.54
     «
    -0.52
    POSITIVE LOGITS
     متعلقه
    0.72
     houſe
    0.71
    expandindo
    0.69
    IndentedString
    0.69
     purpoſe
    0.63
     pleaſure
    0.63
     виправивши
    0.62
     itſelf
    0.61
     Chriſt
    0.60
    didSet
    0.59
    Activations Density 2.084%

    No Known Activations