© 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. 3274
    Prev
    Next
    INDEX
    Explanations

    mentions of international companies, financial transactions, and political associations.

    oai_token-act-pair · gemini-2.0-flash

    Telecom

    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
     shareholders
    -0.74
     shareholder
    -0.73
     fidé
    -0.68
     Montagu
    -0.67
     stockholder
    -0.66
     stockholders
    -0.63
     للاسماء
    -0.63
    ReusableCell
    -0.63
    Kanpo
    -0.62
    ánto
    -0.62
    POSITIVE LOGITS
    хьтан
    0.52
     tiba
    0.44
    RequiresApi
    0.43
    stdc
    0.41
     switch
    0.41
     breve
    0.39
    AsUp
    0.39
     disambiguazione
    0.39
    zī
    0.38
    switch
    0.38
    Activations Density 4.878%

    No Known Activations