© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5588
    Prev
    Next
    INDEX
    Explanations

    statistics in sports articles

    oai_token-act-pair · gemini-2.0-flash

    Sports statistics

    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
    MigrationBuilder
    -1.03
    tagHelperRunner
    -0.74
     Monfieur
    -0.73
    numerusform
    -0.72
    UnusedPrivate
    -0.68
    Демографія
    -0.66
    ]--;
    -0.65
    BrowserModule
    -0.65
     viewType
    -0.62
    ädie
    -0.62
    POSITIVE LOGITS
     to
    0.63
     off
    0.57
     in
    0.57
    chitz
    0.51
    guigu
    0.43
    UseVisualStyle
    0.41
    OBJECTIVE
    0.41
     createContext
    0.41
     and
    0.39
     toe
    0.39
    Activations Density 2.481%

    No Known Activations