© 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. 24-GEMMASCOPE-TRANSCODER-16K
    4. 328
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas involving the letters X, Y, Z, and W, often with exponents and subscripts

    oai_token-act-pair · gemini-2.0-flash

    Mathematical expressions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     w
    -0.84
    w
    -0.66
    webElementXpaths
    -0.57
    wo
    -0.55
     y
    -0.54
    ww
    -0.52
    𝘄
    -0.48
    wdata
    -0.48
     wo
    -0.48
    JoinTable
    -0.46
    POSITIVE LOGITS
     We
    1.02
     You
    0.83
    We
    0.73
     Well
    0.68
    You
    0.67
     Was
    0.66
    expandindo
    0.64
     Vous
    0.64
     Où
    0.63
     Went
    0.63
    Activations Density 4.292%

    No Known Activations