© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14053
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to modifications, testing, or results.

    oai_token-act-pair · gemini-2.0-flash

    fixes mixes releases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     restarts
    -1.23
     declines
    -1.10
     uploads
    -1.08
     collapses
    -1.06
     Increases
    -1.06
     cuts
    -1.06
     ***!
    -1.05
     rises
    -1.05
     washes
    -1.04
    increases
    -1.04
    POSITIVE LOGITS
     change
    0.91
     move
    0.69
     return
    0.63
     break
    0.63
     transfer
    0.61
     set
    0.59
     start
    0.58
    hips
    0.56
     drop
    0.56
     increase
    0.55
    Activations Density 4.457%

    No Known Activations