© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9520
    Prev
    Next
    INDEX
    Explanations

    terms related to car driving assistance systems and features

    oai_token-act-pair · gemini-2.0-flash

    assist alert

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.83
    setViewportView
    -0.82
    sidemargin
    -0.80
    Autoritní
    -0.77
     HasFactory
    -0.69
    setVerticalGroup
    -0.66
     gynnwys
    -0.66
     esternos
    -0.65
    MLLoader
    -0.64
    AsStream
    -0.64
    POSITIVE LOGITS
     motion
    0.46
    InjectAttribute
    0.43
     tension
    0.42
    оне
    0.41
    eg
    0.40
    ко
    0.40
    motion
    0.39
    WHM
    0.39
     пет
    0.38
    NotFound
    0.38
    Activations Density 0.812%

    No Known Activations