© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10065
    Prev
    Next
    INDEX
    Explanations

    words which follow prepositions and certain verb tenses.

    oai_token-act-pair · gemini-2.0-flash

    say "the word the"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    their
    -0.97
     Leurs
    -0.95
     vostri
    -0.94
     chré
    -0.94
     mijne
    -0.92
     våra
    -0.92
     varandra
    -0.91
     nôtre
    -0.90
     vectorielles
    -0.90
     zijne
    -0.87
    POSITIVE LOGITS
     he
    0.82
     they
    0.57
     He
    0.56
    ransition
    0.50
     t
    0.49
     HE
    0.47
    леко
    0.46
     me
    0.45
     +
    0.44
     we
    0.43
    Activations Density 6.375%

    No Known Activations