© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7301
    Prev
    Next
    INDEX
    Explanations

    words related to government, legal agreements or licenses, and business activities using natural resources

    oai_token-act-pair · gemini-2.0-flash

    different languagesMethod: 4Reason: TOP_ACTIVATING_TEXTS are in different languages.different languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Monfieur
    -0.97
     myſelf
    -0.97
     uſed
    -0.95
     itſelf
    -0.94
     pleaſure
    -0.93
     Shakspeare
    -0.91
     purpoſe
    -0.91
     ―――――
    -0.89
     againſt
    -0.89
     ſeveral
    -0.89
    POSITIVE LOGITS
     sind
    0.48
     medical
    0.45
    ,
    0.45
     «
    0.44
     FISCAL
    0.43
    rosa
    0.43
    fiscal
    0.43
     his
    0.42
     socios
    0.42
     thực
    0.42
    Activations Density 0.322%

    No Known Activations