© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7198
    Prev
    Next
    INDEX
    Explanations

    code related to errors and product creation

    oai_token-act-pair · gemini-2.0-flash

    Computer code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     houſe
    -0.89
     uſ
    -0.82
     Monfieur
    -0.81
     whoſe
    -0.81
     Houſe
    -0.81
     myſelf
    -0.81
     purpoſe
    -0.81
     itſelf
    -0.80
     fubject
    -0.79
     himſelf
    -0.78
    POSITIVE LOGITS
     resourceCulture
    0.68
     تضيفلها
    0.57
     FetchType
    0.51
     BorderRadius
    0.48
     ApiException
    0.48
     pools
    0.46
     AssemblyCompany
    0.45
     catalogs
    0.45
     camps
    0.45
     budgets
    0.45
    Activations Density 0.876%

    No Known Activations