© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15483
    Prev
    Next
    INDEX
    Explanations

    something to do with the word churches in source code or data

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     isInitialized
    -0.49
     @"/
    -0.47
     utafitiHapana
    -0.45
    ederos
    -0.45
     seit
    -0.43
     unknownFields
    -0.43
     pinulongan
    -0.42
    يميديا
    -0.41
     Nor
    -0.41
    xaml
    -0.41
    POSITIVE LOGITS
     فريبيس
    0.80
     للمعارف
    0.71
     greateſt
    0.69
    RenderAtEndOf
    0.67
    StoryboardSegue
    0.67
    UnsafeEnabled
    0.60
     ſtate
    0.59
     espagne
    0.57
     Auge
    0.57
    Chham
    0.57
    Activations Density 0.170%

    No Known Activations