© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14229
    Prev
    Next
    INDEX
    Explanations

    words related to cars, especially transmissions and associated parts

    oai_token-act-pair · gemini-2.0-flash

    Car transmissions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    HasAnnotation
    -0.60
    ftagPool
    -0.59
     onOptions
    -0.53
    EDEFAULT
    -0.52
    waitKey
    -0.50
    elemField
    -0.50
    msgSender
    -0.45
    MemoryWarning
    -0.44
    APB
    -0.44
    addGap
    -0.44
    POSITIVE LOGITS
     '\\;'
    0.61
    MERCIAL
    0.54
     swing
    0.53
    فحة
    0.52
    bardier
    0.52
    XtraReports
    0.51
     Diſ
    0.51
    IsContent
    0.51
    myra
    0.51
    Aiheesta
    0.50
    Activations Density 0.945%

    No Known Activations