© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3337
    Prev
    Next
    INDEX
    Explanations

    periods and commas within technical documents

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ↵↵
    -1.01
     purpoſe
    -0.75
     Lastly
    -0.71
     Enfin
    -0.71
     themſelves
    -0.70
    Finally
    -0.69
     quæ
    -0.68
     Finally
    -0.67
    Lastly
    -0.67
     Theſe
    -0.67
    POSITIVE LOGITS
     autorytatywna
    0.62
     NSCoder
    0.57
     <=",
    0.56
     gql
    0.54
     Wicidata
    0.54
    脚注の使い方
    0.54
    actéristique
    0.52
     CURIAM
    0.51
    таратура
    0.51
    ...@
    0.50
    Activations Density 1.052%

    No Known Activations