© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14418
    Prev
    Next
    INDEX
    Explanations

    words and phrases that could be related to scientific, technical or material properties, or ingredients.

    oai_token-act-pair · gemini-2.0-flash

    lungs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     armed
    -0.87
     surrounded
    -0.84
     accompanied
    -0.83
    Covered
    -0.83
     adorned
    -0.80
     covered
    -0.79
    companied
    -0.78
     equipped
    -0.78
     Covered
    -0.76
    accompanied
    -0.75
    POSITIVE LOGITS
     Lung
    1.10
     lung
    1.10
     pulmonary
    0.98
    Lung
    0.98
     lungs
    0.91
     Pulmonary
    0.88
     pulmonar
    0.85
     Bron
    0.79
    Bron
    0.75
     Lungen
    0.75
    Activations Density 7.731%

    No Known Activations