© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9318
    Prev
    Next
    INDEX
    Explanations

    words specifically relating to air conditioning, humidifiers, and dehumidifiers

    oai_token-act-pair · gemini-2.0-flash

    air

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     air
    -2.75
    Air
    -2.42
     Air
    -2.42
    air
    -2.33
     AIR
    -1.91
    AIR
    -1.86
     aire
    -1.45
     luft
    -1.43
     Luft
    -1.34
     lucht
    -1.31
    POSITIVE LOGITS
    RegressionTest
    1.05
    ########.
    1.04
    SourceChecksum
    1.00
     betweenstory
    0.97
    
    0.93
    WebElementEntity
    0.93
    afficheront
    0.89
    expandindo
    0.87
    Personensuche
    0.86
    تقاوى
    0.85
    Activations Density 9.071%

    No Known Activations