© 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. 14147
    Prev
    Next
    INDEX
    Explanations

    reports of law enforcement seeking contact with the public

    oai_token-act-pair · gemini-2.0-flash

    law enforcement

    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
    tagHelperRunner
    -0.96
    jspx
    -0.71
    basicConfig
    -0.68
    parsedMessage
    -0.63
    EndInit
    -0.62
    
    -0.61
    ArgumentParser
    -0.58
     "..\..\..\
    -0.58
     CreateTagHelper
    -0.57
    UnknownFieldSet
    -0.57
    POSITIVE LOGITS
    FetchType
    0.54
     hijau
    0.48
     devint
    0.47
    Spoljašnje
    0.46
    jewództ
    0.43
     arrivent
    0.43
     división
    0.43
     montrer
    0.42
    новништво
    0.42
     (;;
    0.42
    Activations Density 0.819%

    No Known Activations