© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13338
    Prev
    Next
    INDEX
    Explanations

    mathematical language, especially terms like "determinant" and "volume".

    oai_token-act-pair · gemini-2.0-flash

    determinant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Theſe
    -0.74
     Beſ
    -0.71
     myſelf
    -0.71
     Efq
    -0.70
     Monfieur
    -0.68
     Jefus
    -0.67
     Eſ
    -0.66
     himſelf
    -0.65
     laſt
    -0.62
     juſ
    -0.60
    POSITIVE LOGITS
     الحره
    0.82
    <bos>
    0.75
     незавершена
    0.71
    transQ
    0.68
     CreateTagHelper
    0.66
    DockStyle
    0.66
     EconPapers
    0.65
    MessageTagHelper
    0.60
    Попис
    0.58
    TypedDataSet
    0.57
    Activations Density 1.606%

    No Known Activations