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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13522
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to find a variety of words that have little semantic connection with activations depending on surrounding text

    oai_token-act-pair · gemini-2.0-flash

    distance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    queryInterface
    -0.63
    
    -0.61
     onCancelled
    -0.60
    endphp
    -0.59
     ModelExpression
    -0.58
    fjspx
    -0.57
    gypte
    -0.55
    Portály
    -0.55
    ProgressHUD
    -0.55
    setBold
    -0.55
    POSITIVE LOGITS
     distance
    2.19
     Distance
    1.85
    distance
    1.83
     distances
    1.80
     far
    1.76
    Distance
    1.76
     miles
    1.68
     DISTANCE
    1.63
    far
    1.58
     distant
    1.45
    Activations Density 4.403%

    No Known Activations