© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 226
    Prev
    Next
    INDEX
    Explanations

    technical, academic language related to mathematics and proofs

    oai_token-act-pair · gemini-2.0-flash

    math/academic papers

    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
    Negative Logits
    ODO
    -0.45
    ЦИЯ
    -0.43
     Bez
    -0.42
    lamento
    -0.42
     ekster
    -0.41
     verre
    -0.41
    xygen
    -0.40
    each
    -0.40
    模
    -0.40
    tanaman
    -0.39
    POSITIVE LOGITS
    <bos>
    1.09
     kasarigan
    1.02
     שוליים
    0.90
     متعلقه
    0.83
    RegressionTest
    0.82
    Geplaatst
    0.81
    /**
    0.77
    Personendaten
    0.74
    ########.
    0.74
     kaarangay
    0.73
    Activations Density 5.832%

    No Known Activations