© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11937
    Prev
    Next
    INDEX
    Explanations

    a mix of numbers, math symbols, and legal jargon

    oai_token-act-pair · gemini-2.0-flash

    1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    fjspx
    -0.51
    الدراسه
    -0.51
    <?>
    -0.50
     scams
    -0.49
    graphicx
    -0.47
     chio
    -0.47
    yonel
    -0.46
     utafitiHapana
    -0.46
     {};
    -0.45
    setFocusable
    -0.45
    POSITIVE LOGITS
    -\
    0.77
    MessageTagHelper
    0.73
    writeFieldEnd
    0.70
    ArrowToggle
    0.70
     >=",
    0.69
    +\
    0.68
    WithMany
    0.63
    IVEREF
    0.60
    يكب
    0.59
    StructEnd
    0.59
    Activations Density 8.479%

    No Known Activations