© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10819
    Prev
    Next
    INDEX
    Explanations

    mentions of Iowa, especially in the context of the University or its Governor

    oai_token-act-pair · gemini-2.0-flash

    Iowa locations

    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
     Roskov
    -0.86
    hoeddwyd
    -0.82
     Савезне
    -0.77
     архивлан
    -0.75
     onItemClick
    -0.68
    tagHelperRunner
    -0.64
     protoimpl
    -0.62
    EndGlobalSection
    -0.62
    adpleegd
    -0.61
    accompag
    -0.61
    POSITIVE LOGITS
     Inter
    0.52
     E
    0.52
    花板
    0.50
     M
    0.48
    frastructure
    0.48
    laye
    0.47
    Inter
    0.47
     Stoll
    0.46
    orek
    0.46
     H
    0.46
    Activations Density 1.277%

    No Known Activations