© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9828
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to players' statistics in sports games.

    oai_token-act-pair · gemini-2.0-flash

    Sports reporting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     GoogleFonts
    -0.82
    viewDidLoad
    -0.75
    ChildScrollView
    -0.74
    ftagPool
    -0.74
    RectangleBorder
    -0.72
    mapStateToProps
    -0.69
    UserScript
    -0.67
    NUMX
    -0.66
     Efq
    -0.66
    LayoutStyle
    -0.65
    POSITIVE LOGITS
    Geplaatst
    0.52
     AssemblyCulture
    0.44
     send
    0.42
     extend
    0.39
    baran
    0.38
    BeginContext
    0.38
    <eos>
    0.38
    apat
    0.38
     ']
    0.38
    iotensin
    0.37
    Activations Density 0.459%

    No Known Activations