© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7462
    Prev
    Next
    INDEX
    Explanations

    this neuron seems to be identifying sentences containing references to artistic and historical contexts, including names of people, places, and periods

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Napoleon
    -0.59
     nineteenth
    -0.56
     Romantic
    -0.52
     Napoleonic
    -0.52
    الحياه
    -0.52
     Barat
    -0.51
     Napole
    -0.51
    Empereur
    -0.51
     romántico
    -0.49
     Nineteenth
    -0.48
    POSITIVE LOGITS
    contentLoaded
    0.68
    Rhestr
    0.65
     ostavi
    0.60
     protoimpl
    0.59
    Dropout
    0.58
    Personensuche
    0.57
    loyment
    0.56
    цездатний
    0.56
    gebras
    0.55
     Aires
    0.54
    Activations Density 0.559%

    No Known Activations