© 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. 9438
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and expressions

    oai_token-act-pair · gemini-2.0-flash

    math expressions

    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
     parkir
    -0.54
    databinding
    -0.54
    arach
    -0.53
    isSet
    -0.52
    Parcelize
    -0.51
    ecore
    -0.51
     phóng
    -0.51
     Pase
    -0.50
    Trou
    -0.50
     IgG
    -0.49
    POSITIVE LOGITS
    ########.
    0.75
     Mahomet
    0.69
     Jefus
    0.69
     myſelf
    0.67
     pleaſure
    0.66
     Wikimedijinoj
    0.66
     themſelves
    0.66
    tinyos
    0.66
     fubject
    0.65
     pleaf
    0.65
    Activations Density 4.725%

    No Known Activations