© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 3795
    Prev
    Next
    INDEX
    Explanations

    measurements or specifications related to vehicles and engines

    oai_token-act-pair · gemini-2.0-flash

    Automotive technology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Drivers
    -0.50
     racing
    -0.49
     chassis
    -0.48
     motorsport
    -0.48
     racer
    -0.46
     Chassis
    -0.46
     Abt
    -0.45
     lap
    -0.44
    Chassis
    -0.44
     drivers
    -0.44
    POSITIVE LOGITS
    NOPQRST
    0.89
     ModelExpression
    0.68
    
    0.63
     ujednoznacz
    0.63
    ContentAsync
    0.63
    WRENCE
    0.63
    Datuak
    0.60
    ollectionView
    0.60
    tellation
    0.59
     esternos
    0.57
    Activations Density 0.638%

    No Known Activations