© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14737
    Prev
    Next
    INDEX
    Explanations

    words related to nationality, citizenship, or being born in a certain place

    oai_token-act-pair · gemini-2.0-flash

    state abbreviations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Houſe
    -0.67
     Anſ
    -0.64
     Theſe
    -0.64
     Diſ
    -0.63
     CreateTagHelper
    -0.59
    ')")
    -0.59
    TableAdapter
    -0.59
     houſe
    -0.57
     Aceh
    -0.56
     Monfieur
    -0.56
    POSITIVE LOGITS
     Ne
    0.70
     Ver
    0.69
     Virgin
    0.68
    EndProject
    0.62
     Kent
    0.62
     Miss
    0.61
    Virgin
    0.59
     Sou
    0.59
    Miss
    0.55
     Color
    0.54
    Activations Density 1.293%

    No Known Activations