© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 2914
    Prev
    Next
    INDEX
    Explanations

    dollar signs, particularly those indicating mathematical expressions in LaTeX

    oai_token-act-pair · gemini-2.0-flash

    dollar signs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    .}~\
    -0.90
    "],
    -0.90
     native
    -0.82
     different
    -0.81
    "]="
    -0.80
    .}(
    -0.80
    bibinfo
    -0.80
    citenamefont
    -0.79
    ]<<"
    -0.77
    BibitemShut
    -0.77
    POSITIVE LOGITS
    <bos>
    1.77
     împre
    0.85
    ↵
    0.81
    I
    0.68
     maș
    0.68
     înal
    0.65
     poveznice
    0.65
     löyty
    0.65
     nacionais
    0.64
     perchè
    0.63
    Activations Density 1.024%

    No Known Activations