© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13427
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on a variety of different things that seem to correlate to longer sentences, but it is hard to deduce a relationship or theme

    oai_token-act-pair · gemini-2.0-flash

    located

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    find
    -0.81
     find
    -0.79
    finding
    -0.77
     finding
    -0.75
    FIND
    -0.74
     propOrder
    -0.73
    Find
    -0.73
    Finding
    -0.73
     Finding
    -0.70
     FIND
    -0.70
    POSITIVE LOGITS
     located
    1.93
     Located
    1.66
    located
    1.51
    Located
    1.47
     localizado
    1.14
     ubicado
    1.09
     Location
    1.05
    Location
    1.02
     LOCATION
    1.01
     localizada
    1.01
    Activations Density 4.799%

    No Known Activations