© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14992
    Prev
    Next
    INDEX
    Explanations

    related to event descriptions, especially those following prepositions or related to Brexit

    oai_token-act-pair · 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
     MenuView
    -0.66
     Paglinawan
    -0.55
    InvalidProtocol
    -0.54
    DetailComponent
    -0.53
    PubKey
    -0.51
    uxxxx
    -0.50
     Reiss
    -0.49
    èdia
    -0.49
    otas
    -0.48
    TestingModule
    -0.48
    POSITIVE LOGITS
    webElementXpaths
    0.70
    XmlAccessorType
    0.60
    IntoConstraints
    0.57
    Ữ
    0.55
     Dazu
    0.51
     maisha
    0.51
    MLLoader
    0.50
    irà
    0.50
     Duch
    0.48
     breakpoint
    0.48
    Activations Density 1.836%

    No Known Activations