© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15629
    Prev
    Next
    INDEX
    Explanations

    words describing stylish car design

    oai_token-act-pair · gemini-2.0-flash

    terms related to vehicle lighting

    np_token-act-pair-logits · gpt-4o-mini

    lights

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ConstraintMaker
    -0.63
    tagHelperRunner
    -0.61
    ThroughAttribute
    -0.59
    AndEndTag
    -0.59
    webElementXpaths
    -0.57
     propOrder
    -0.57
    
    -0.54
    DockStyle
    -0.52
    GEBURTSDATUM
    -0.49
     EconPapers
    -0.48
    POSITIVE LOGITS
     lights
    0.82
    lights
    0.73
     tail
    0.73
     signal
    0.70
     ta
    0.69
     blink
    0.67
     fog
    0.66
    Lights
    0.65
     Head
    0.64
     signals
    0.63
    Activations Density 0.867%

    No Known Activations