© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8190
    Prev
    Next
    INDEX
    Explanations

    uses of the words 'is', 'are', or 'was' immediately following 'there', 'the', 'a', 'that', or 'this' or with the word 'not' nearby

    oai_token-act-pair · gemini-2.0-flash

    is/was

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     những
    -0.79
     arguments
    -0.77
     episodes
    -0.76
     gestures
    -0.75
     variations
    -0.75
     members
    -0.74
     subsidiaries
    -0.73
     embodiments
    -0.73
     finalists
    -0.72
     contenders
    -0.72
    POSITIVE LOGITS
     vœux
    0.72
     épaules
    0.69
     lèvres
    0.64
     genoux
    0.58
     aikaa
    0.55
     inconvénients
    0.53
     oreilles
    0.53
     vérit
    0.52
     gouvernements
    0.50
    lería
    0.49
    Activations Density 5.106%

    No Known Activations