© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11611
    Prev
    Next
    INDEX
    Explanations

    mentions of the Deferred Action for Childhood Arrivals (DACA) immigration policy and related terms

    oai_token-act-pair · gemini-2.0-flash

    ACA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    -0.85
     surla
    -0.75
     дописавши
    -0.73
    ValueStyle
    -0.73
    ləş
    -0.71
     lyre
    -0.70
     IService
    -0.70
     therefrom
    -0.69
    voyez
    -0.65
     linkovi
    -0.65
    POSITIVE LOGITS
     Immigration
    0.74
    immigration
    0.74
     immigration
    0.68
    Immigration
    0.66
    immig
    0.61
     visa
    0.58
     di
    0.57
     Visa
    0.56
     immig
    0.55
     deported
    0.55
    Activations Density 0.965%

    No Known Activations