© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6105
    Prev
    Next
    INDEX
    Explanations

    the opening parts of news articles about some incident

    oai_token-act-pair · gemini-2.0-flash

    Names

    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
     Monfieur
    -0.91
     cauſe
    -0.90
     Chriftian
    -0.89
     reaſon
    -0.88
     Efq
    -0.87
     leaſt
    -0.85
     greateſt
    -0.85
     myſelf
    -0.85
     preſent
    -0.84
     houſe
    -0.84
    POSITIVE LOGITS
     Ben
    0.61
    Ben
    0.53
     Meghan
    0.52
     Donald
    0.50
     Boris
    0.50
     Tom
    0.49
     Trump
    0.47
     Margot
    0.46
    Donald
    0.45
     Bin
    0.45
    Activations Density 11.486%

    No Known Activations