© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12970
    Prev
    Next
    INDEX
    Explanations

    information about baseball games, especially scores, players, and stats

    oai_token-act-pair · gemini-2.0-flash

    baseball game events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    хьтан
    -0.54
     protoimpl
    -0.53
    RunAsync
    -0.52
     propOrder
    -0.47
     illa
    -0.45
    ContentAsync
    -0.45
    ArrowToggle
    -0.45
    PreferredItem
    -0.44
     reproduction
    -0.44
    fromnode
    -0.44
    POSITIVE LOGITS
     debout
    0.62
     논
    0.60
     Row
    0.58
     disambiguazione
    0.57
    base
    0.55
     row
    0.55
     base
    0.54
     المعيارى
    0.54
     Cair
    0.53
    xue
    0.53
    Activations Density 1.400%

    No Known Activations