© 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. 2974
    Prev
    Next
    INDEX
    Explanations

    capitalized word fragments in the middle of words of legal and scientific documents

    oai_token-act-pair · 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
     
    -0.89
    ,
    -0.88
      
    -0.86
    .
    -0.82
     (
    -0.82
    …
    -0.79
    ↵
    -0.79
     ,
    -0.79
     –
    -0.79
    ...
    -0.79
    POSITIVE LOGITS
     سكانية
    0.94
    ValueStyle
    0.90
     varandra
    0.90
     Efq
    0.89
     Houſe
    0.85
     itſelf
    0.84
     doubtnut
    0.83
     photolibrary
    0.83
     myſelf
    0.81
    Vidite
    0.79
    Activations Density 2.276%

    No Known Activations