© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12687
    Prev
    Next
    INDEX
    Explanations

    LaTeX code and mathematical expressions with bracket-like syntax

    oai_token-act-pair · gemini-2.0-flash

    LaTeX code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    <bos>
    -1.27
    '
    -0.69
    ↵
    -0.66
    .
    -0.62
    ’
    -0.61
    <h2>
    -0.61
    left
    -0.60
    def
    -0.57
    The
    -0.56
    ">
    -0.56
    POSITIVE LOGITS
     Roskov
    1.31
    bibinfo
    0.97
    BibitemShut
    0.95
    InjectAttribute
    0.91
    bibfield
    0.89
     myſelf
    0.81
     ―――――
    0.81
     ――――
    0.81
    esterday
    0.81
    citenamefont
    0.76
    Activations Density 0.320%

    No Known Activations