© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15060
    Prev
    Next
    INDEX
    Explanations

    section headers, lemmas, theorems and table declarations in LaTeX documents

    oai_token-act-pair · gemini-2.0-flash

    mathematical lemmas and theorems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    migrationBuilder
    -0.62
    ;">
    -0.53
    riwal
    -0.52
     nors
    -0.52
     Battista
    -0.51
     actionMode
    -0.50
     disambiguazione
    -0.49
    ̀
    -0.49
    OrNil
    -0.47
    umbuhan
    -0.45
    POSITIVE LOGITS
     يتيمه
    0.69
    <bos>
    0.62
    Viitteet
    0.59
     مشين
    0.57
    enterOuterAlt
    0.57
     springfox
    0.57
    parsedMessage
    0.57
     estekak
    0.54
    脚注の使い方
    0.52
    saraba
    0.52
    Activations Density 5.019%

    No Known Activations