© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11678
    Prev
    Next
    INDEX
    Explanations

    legal and governmental terms and phrases

    oai_token-act-pair · gemini-2.0-flash

    legal ordinances and regulations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    <bos>
    -0.59
     الرياضيه
    -0.41
    例文帳に追加
    -0.41
    ïti
    -0.40
    /
    -0.39
     cocaína
    -0.39
    有限公司
    -0.38
    mektedir
    -0.37
     oport
    -0.37
     g
    -0.36
    POSITIVE LOGITS
    出版年
    1.09
     myſelf
    1.08
     Efq
    1.08
     Monfieur
    0.95
     uſe
    0.95
     Majefty
    0.93
     himſelf
    0.91
     itſelf
    0.91
     Jefus
    0.91
     deſt
    0.91
    Activations Density 1.107%

    No Known Activations