© 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
    2. Gemma-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 8834
    Prev
    Next
    INDEX
    Explanations

    the neuron seems to be looking for references to confederations, conspiracy, baseball teams, college campuses, and linotype machines

    oai_token-act-pair · gemini-2.0-flash

    Historical events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ndig
    -0.57
     AssemblyCulture
    -0.56
    ingga
    -0.54
    !*\
    -0.54
    GEBURTSDATUM
    -0.53
    مصادر
    -0.52
    Collegamenti
    -0.52
    makeText
    -0.50
     bền
    -0.49
     ISNI
    -0.49
    POSITIVE LOGITS
     ContentValues
    0.59
    íslu
    0.57
    MLLoader
    0.55
    UrlResolution
    0.55
     ویکی‌پدیا
    0.52
     viewType
    0.50
    INSEE
    0.49
    --)
    
    0.48
     numberWith
    0.48
     lasso
    0.47
    Activations Density 1.851%

    No Known Activations