© 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. 13878
    Prev
    Next
    INDEX
    Explanations

    numbers, especially integers and dates/times, sometimes with formatting characters around the numbers

    oai_token-act-pair · gemini-2.0-flash

    code and programming

    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
    3
    -1.55
     Three
    -1.25
    ３
    -1.20
     three
    -1.13
    Three
    -1.10
    三
    -1.09
     Thirty
    -1.06
     THREE
    -1.05
     ३
    -1.05
     III
    -1.02
    POSITIVE LOGITS
    DoubleQuotes
    0.87
    openConnection
    0.73
    endphp
    0.71
    saraba
    0.68
    oneofs
    0.67
    UserScript
    0.65
    存于互联网档案馆
    0.64
     AssemblyCulture
    0.64
     Anfitrión
    0.60
    SequentialGroup
    0.60
    Activations Density 2.256%

    No Known Activations