© 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. 5067
    Prev
    Next
    INDEX
    Explanations

    text from legal documents or news articles

    oai_token-act-pair · gemini-2.0-flash

    Legal & academic text

    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
    ">//
    -0.94
    ✨:
    -0.73
     Shells
    -0.70
     Mesin
    -0.69
     Lighter
    -0.69
     Água
    -0.68
     Tubes
    -0.67
     Bulb
    -0.67
     Wires
    -0.67
     Bottles
    -0.66
    POSITIVE LOGITS
     Aca
    0.50
     Academic
    0.48
    Jud
    0.46
     Legisl
    0.46
    Juris
    0.45
     Faith
    0.45
    Public
    0.44
    Doc
    0.44
     Doc
    0.44
     Judicial
    0.44
    Activations Density 8.013%

    No Known Activations