© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6379
    Prev
    Next
    INDEX
    Explanations

    vocabulary related to car interiors

    oai_token-act-pair · gemini-2.0-flash

    car interiors

    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
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.96
     doInBackground
    -0.76
     تضيفلها
    -0.66
    kháu
    -0.60
    HasForeignKey
    -0.58
    reportWebVitals
    -0.56
     Audiodateien
    -0.55
    
    -0.54
     bygger
    -0.54
    XmlAccessType
    -0.54
    POSITIVE LOGITS
     mergeFrom
    0.47
     elbow
    0.47
     sun
    0.47
     board
    0.46
     arm
    0.45
    stateMutability
    0.43
    叶修
    0.43
     BorderRadius
    0.43
    mats
    0.43
     finished
    0.42
    Activations Density 0.768%

    No Known Activations