© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11035
    Prev
    Next
    INDEX
    Explanations

    terms related to sports matches and opponents, some math terms, and location of a bug

    oai_token-act-pair · gemini-2.0-flash

    Sports opponents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    trui
    -0.52
    MathML
    -0.52
    okhttp
    -0.52
     AspNetCore
    -0.47
     Extragalactic
    -0.47
    లాలు
    -0.46
     JADX
    -0.45
    աքին
    -0.44
    PRNewswire
    -0.44
    czy
    -0.43
    POSITIVE LOGITS
    httphttps
    0.68
    tonode
    0.61
     esternos
    0.60
     myſelf
    0.60
    ValueStyle
    0.55
     Theſe
    0.54
     IBOutlet
    0.54
     CreateTagHelper
    0.54
    ^(@)
    0.51
     itſelf
    0.51
    Activations Density 0.402%

    No Known Activations