© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13737
    Prev
    Next
    INDEX
    Explanations

    the word "slow" and related words

    oai_token-act-pair · gemini-2.0-flash

    slow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     slow
    -2.58
    slow
    -2.38
    Slow
    -2.34
     Slow
    -2.27
     SLOW
    -1.97
     slower
    -1.80
    SLOW
    -1.73
     slows
    -1.69
     slowed
    -1.58
     slowing
    -1.56
    POSITIVE LOGITS
     financière
    0.57
    BagLayout
    0.57
    Према
    0.57
     juridique
    0.57
     indépend
    0.54
     heterogeneous
    0.54
    
    0.51
    YourGuide
    0.51
    zzleHttp
    0.50
     heterogeneity
    0.50
    Activations Density 1.211%

    No Known Activations