© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8019
    Prev
    Next
    INDEX
    Explanations

    the word "pretty" with varying degrees of activation depending on context

    oai_token-act-pair · gemini-2.0-flash

    pretty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     pretty
    -2.42
    Pretty
    -2.16
    pretty
    -2.14
     Pretty
    -1.98
     PRET
    -1.29
     fairly
    -0.97
    <bos>
    -0.96
     prettiest
    -0.85
     quite
    -0.84
     Fairly
    -0.84
    POSITIVE LOGITS
    URLException
    0.78
    
    0.68
    niów
    0.66
    InSection
    0.65
    )');
    0.63
    ῖς
    0.63
    )')
    0.62
    原始内容存档于
    0.62
    })();
    0.62
     FileInputStream
    0.60
    Activations Density 1.318%

    No Known Activations