© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14581
    Prev
    Next
    INDEX
    Explanations

    sentences regarding closures, job losses, economics, centers and dates, especially with the words "to close".

    oai_token-act-pair · gemini-2.0-flash

    closing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    tvguidetime
    -0.65
    出版年
    -0.57
    ########.
    -0.55
     betweenstory
    -0.53
    BarButtonItem
    -0.49
     AssemblyCompany
    -0.48
    +#+#
    -0.48
    bitField
    -0.47
    Merkmale
    -0.46
    arschu
    -0.46
    POSITIVE LOGITS
     closing
    2.22
     Closing
    2.13
     closed
    2.09
     Closed
    1.97
     closes
    1.94
    Closing
    1.94
    closed
    1.90
     closure
    1.88
    closing
    1.87
    Closed
    1.78
    Activations Density 4.007%

    No Known Activations