© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11582
    Prev
    Next
    INDEX
    Explanations

    location names and words indicating geography

    oai_token-act-pair · gemini-2.0-flash

    foreign or multi-language phrases

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    toHaveBeenCalled
    -0.59
    BASEPATH
    -0.58
    /**
    -0.56
    XmlType
    -0.56
     comigo
    -0.54
    letka
    -0.51
     sleeves
    -0.49
    futbolista
    -0.47
     culturelles
    -0.47
     blanche
    -0.47
    POSITIVE LOGITS
    rungsseite
    0.75
     AssemblyCulture
    0.75
    twimg
    0.63
    出版年
    0.63
    sidemargin
    0.62
     وتسجيلات
    0.60
    AsUp
    0.59
    addCriterion
    0.59
     lenker
    0.59
     Италијани
    0.57
    Activations Density 0.575%

    No Known Activations