© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3393
    Prev
    Next
    INDEX
    Explanations

    words related to military history, service, and genealogy

    oai_token-act-pair · gemini-2.0-flash

    military service and injury

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    WebServlet
    -0.53
     vété
    -0.52
     Partagez
    -0.52
     gyhoeddwyd
    -0.52
    İM
    -0.50
     allegorical
    -0.49
     raconter
    -0.49
     getCity
    -0.49
    ItemBackground
    -0.49
    jącym
    -0.48
    POSITIVE LOGITS
    DockStyle
    0.65
    WithIOException
    0.63
    といけない
    0.55
    Referencies
    0.54
     للمعارف
    0.52
    testens
    0.51
     Roskov
    0.51
    writerow
    0.50
    Източници
    0.49
    はじめに
    0.49
    Activations Density 38.576%

    No Known Activations