© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11730
    Prev
    Next
    INDEX
    Explanations

    technical language, related to scientific notation, or the medical field, especially in relation to patient data and lab results

    oai_token-act-pair · gemini-2.0-flash

    Research papers, medical reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     AsyncTask
    -0.49
     réflex
    -0.49
    pulumi
    -0.48
     perd
    -0.47
     namens
    -0.46
    ❋
    -0.46
     shutters
    -0.46
    }));
    -0.46
     дописавши
    -0.45
    FormBorderStyle
    -0.45
    POSITIVE LOGITS
     UnityEditor
    0.62
     BaseActivity
    0.61
    RegressionTest
    0.61
    RetentionPolicy
    0.60
    ]--;
    0.59
     상세
    0.59
    XmlAccessType
    0.59
     CiNii
    0.57
    koku
    0.56
    amaged
    0.56
    Activations Density 1.905%

    No Known Activations