© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13784
    Prev
    Next
    INDEX
    Explanations

    a variety of programming-related terms, including file operations, server requests, and event handling.

    oai_token-act-pair · gemini-2.0-flash

    _

    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
     nahilalakip
    -1.43
     متعلقه
    -1.38
     AssemblyCulture
    -1.29
     propOrder
    -1.29
     surla
    -1.29
     חיצוניים
    -1.27
     autorytatywna
    -1.25
    tvguidetime
    -1.23
     Efq
    -1.23
     مشين
    -1.20
    POSITIVE LOGITS
    F
    0.48
    R
    0.45
    M
    0.43
    ↵
    0.39
    U
    0.37
    3
    0.36
    1
    0.36
    W
    0.36
    S
    0.36
    A
    0.36
    Activations Density 0.721%

    No Known Activations