© 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. 2885
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly related to UI elements, event handling, or boolean logic

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
     
    -1.41
    <eos>
    -1.37
    ↵
    -1.36
    ↵↵
    -1.34
     (
    -1.26
    ,
    -1.23
    .
    -1.22
      
    -1.21
    -
    -1.18
    '
    -1.18
    POSITIVE LOGITS
     myſelf
    3.28
     Efq
    3.22
     Theſe
    3.11
     itſelf
    3.09
     Monfieur
    2.88
     Jefus
    2.86
     himſelf
    2.69
     themſelves
    2.64
     ſeveral
    2.63
     purpoſe
    2.61
    Activations Density 11.087%

    No Known Activations