© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5112
    Prev
    Next
    INDEX
    Explanations

    words related to politics and government, their documents and proceedings

    oai_token-act-pair · gemini-2.0-flash

    formal communications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Telling
    -0.78
     Telling
    -0.72
     Having
    -0.67
    Having
    -0.66
     Wearing
    -0.63
     refusé
    -0.61
    Focusing
    -0.61
     Addressing
    -0.61
     незавершена
    -0.60
    dealing
    -0.59
    POSITIVE LOGITS
    出版年
    0.81
    nezeu
    0.62
    SharedDtor
    0.55
    FormTagHelper
    0.52
    CloseOperation
    0.51
    lab
    0.50
    dap
    0.48
     contrario
    0.46
     approaching
    0.45
    ArrowToggle
    0.45
    Activations Density 6.199%

    No Known Activations