© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14415
    Prev
    Next
    INDEX
    Explanations

    text about national or international government resolutions and related activity.

    oai_token-act-pair · gemini-2.0-flash

    references to the UN or United Nations

    np_token-act-pair-logits · gpt-4o-mini

    United Nations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    StoryboardSegue
    -0.62
     '{@
    -0.59
    出版年
    -0.57
     Obrador
    -0.57
    NewGuid
    -0.56
    Diwedd
    -0.55
     Ephraim
    -0.55
    WaitGroup
    -0.54
     DBNull
    -0.54
     ffilmiau
    -0.54
    POSITIVE LOGITS
     UN
    2.11
     United
    1.83
    UN
    1.77
    United
    1.61
     UNITED
    1.37
     Un
    1.20
    UNITED
    1.19
     UNS
    1.18
     UNA
    1.12
    united
    1.10
    Activations Density 1.689%

    No Known Activations