© 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. 2911
    Prev
    Next
    INDEX
    Explanations

    a word ending in "ants," especially in a medical, scientific, or legal context, often with an additional preceding word

    oai_token-act-pair · gemini-2.0-flash

    infection/disease prevention

    np_max-act · gemini-2.0-flash

    say "punctuation"

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    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
     âgées
    -0.94
     élevées
    -0.91
     supérieures
    -0.90
     termica
    -0.89
     réguli
    -0.89
     complètes
    -0.88
     feroit
    -0.87
     scolaires
    -0.86
     fermés
    -0.85
     religieuses
    -0.84
    POSITIVE LOGITS
     direct
    0.62
     top
    0.55
     point
    0.52
     acc
    0.52
     comment
    0.52
     ever
    0.49
     capital
    0.49
     different
    0.49
     par
    0.49
    ged
    0.49
    Activations Density 1.786%

    No Known Activations