© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 439
    Prev
    Next
    INDEX
    Explanations

    the word "or" as well as conjunctions

    oai_token-act-pair · gemini-2.0-flash

    or

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    TagMode
    -1.09
     defaultstate
    -0.87
    httphttps
    -0.86
     disponibilités
    -0.80
    сылкі
    -0.79
     تضيفلها
    -0.79
     HasFactory
    -0.77
    存于互联网档案馆
    -0.76
    AndEndTag
    -0.75
    contentLoaded
    -0.72
    POSITIVE LOGITS
     else
    0.74
     equivalently
    0.65
     alternatively
    0.63
     seja
    0.62
     whatever
    0.60
    ients
    0.60
     even
    0.60
     herhangi
    0.60
    else
    0.60
     rather
    0.58
    Activations Density 2.114%

    No Known Activations