© 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. 13844
    Prev
    Next
    INDEX
    Explanations

    mentions of government units or organizations, especially those related to law enforcement and intelligence.

    oai_token-act-pair · gemini-2.0-flash

    UK police organizations

    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
    脚注の使い方
    -0.58
    webElementGuid
    -0.51
    principalTable
    -0.50
    Transkript
    -0.49
    AndroidJUnit
    -0.49
    onViewCreated
    -0.47
    readAs
    -0.47
    پیوند
    -0.46
     estekak
    -0.46
    transQ
    -0.46
    POSITIVE LOGITS
     pinulongan
    0.62
    はじめに
    0.60
    }")
    0.60
    ')):
    0.58
    dymyr
    0.58
     ""){
    0.58
     Pc
    0.58
    RenderAtEndOf
    0.53
    ClientSize
    0.53
    "}")
    0.52
    Activations Density 1.908%

    No Known Activations