© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3006
    Prev
    Next
    INDEX
    Explanations

    technical mentions of fuel, fuel cells, and fuel consumption pertaining to vehicles

    oai_token-act-pair · gemini-2.0-flash

    fuel

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    DataAnnotations
    -0.52
    SourceChecksum
    -0.50
    queryInterface
    -0.48
     idéia
    -0.46
     aceptas
    -0.46
     psicológica
    -0.46
     Merv
    -0.45
     Erbe
    -0.45
    Odkazy
    -0.44
    umus
    -0.44
    POSITIVE LOGITS
     nakalista
    0.69
    TestingModule
    0.69
     wireType
    0.68
    abestanden
    0.66
     AssemblyProduct
    0.61
    IsMutable
    0.58
    IonicModule
    0.58
    География
    0.57
    lotte
    0.57
     Normdatei
    0.57
    Activations Density 1.291%

    No Known Activations