© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1138
    Prev
    Next
    INDEX
    Explanations

    legal or technical language for maritime oil rigs, geographical locations and company names

    oai_token-act-pair · gemini-2.0-flash

    legal, maritime context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     presented
    -0.61
     PRESENTED
    -0.60
     Presented
    -0.54
    há
    -0.52
     presents
    -0.49
     שוליים
    -0.48
    presented
    -0.48
     presenting
    -0.47
    ãng
    -0.46
     Presenting
    -0.46
    POSITIVE LOGITS
     Monfieur
    0.73
     myſelf
    0.72
     Архів
    0.69
    GEBURTSDATUM
    0.66
     متعلقه
    0.66
    SBATCH
    0.64
     itſelf
    0.64
     abortions
    0.62
     himſelf
    0.62
    MessageTagHelper
    0.62
    Activations Density 1.850%

    No Known Activations