© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11147
    Prev
    Next
    INDEX
    Explanations

    multiple different things including trails and outdoor travel, and biological processes involving cells

    oai_token-act-pair · gemini-2.0-flash

    Past, old, or former

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     broken
    -1.37
    broken
    -1.35
    Broken
    -1.26
     lost
    -1.23
     Broken
    -1.20
     destroyed
    -1.20
     Lost
    -1.20
     LOST
    -1.19
    Lost
    -1.19
    lost
    -1.19
    POSITIVE LOGITS
     defaultstate
    0.56
    createCanvas
    0.54
    }{*}{
    0.52
    ValueStyle
    0.49
    afy
    0.48
    kháu
    0.48
    ChildScrollView
    0.47
    hashtags
    0.46
    tagHelper
    0.45
    MigrationBuilder
    0.45
    Activations Density 4.950%

    No Known Activations