© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1648
    Prev
    Next
    INDEX
    Explanations

    LaTeX code for mathematical equations.

    oai_token-act-pair · gemini-2.0-flash

    mathematical/code 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
    <b>
    -1.75
    //
    -1.08
    dfrac
    -0.87
    <strong>
    -0.82
     **
    -0.80
    \
    -0.73
     //
    -0.70
    <em>
    -0.69
    </em>
    -0.63
    mathbf
    -0.58
    POSITIVE LOGITS
    — 
    0.78
    ftagPool
    0.75
    énario
    0.71
     settling
    0.71
    InvalidProtocol
    0.70
    Архівовано
    0.70
    $.
    0.69
    يميديا
    0.68
     settlement
    0.68
    <i>
    0.68
    Activations Density 1.124%

    No Known Activations