© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2836
    Prev
    Next
    INDEX
    Explanations

    language from legal documents around phrases like "pursuant to"

    oai_token-act-pair · gemini-2.0-flash

    ant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    tagHelperRunner
    -1.00
    ########.
    -0.90
    +#+#
    -0.88
     Paglinawan
    -0.87
     Normdatei
    -0.83
     lenker
    -0.79
    principalColumn
    -0.77
    ⓧ
    -0.75
    twimg
    -0.74
     EconPapers
    -0.73
    POSITIVE LOGITS
    <bos>
    0.74
    ...
    0.63
    "
    0.55
    '
    0.51
    <
    0.50
    at
    0.50
    “
    0.50
    ījum
    0.49
    if
    0.49
    )))
    0.49
    Activations Density 3.643%

    No Known Activations