© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 14221
    Prev
    Next
    INDEX
    Explanations

    angle bracket characters and the word clinical strongly

    oai_token-act-pair · gemini-2.0-flash

    </

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Efq
    -2.06
     $_"
    -1.72
     myſelf
    -1.70
     doubtnut
    -1.67
    ^(@)
    -1.63
    ITERATURE
    -1.57
     Theſe
    -1.56
    $.
    
    -1.54
     iſt
    -1.54
     }}$}
    -1.53
    POSITIVE LOGITS
    "
    1.50
    ↵↵
    1.48
    (
    1.41
    ↵
    1.34
    *
    1.32
    '
    1.30
        
    1.23
    [
    1.22
    \
    1.22
    The
    1.21
    Activations Density 0.279%

    No Known Activations