© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14896
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to soccer games, seasons, and management.

    oai_token-act-pair · gemini-2.0-flash

    Sports, winning, and losing

    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
    verwijspagina
    -0.71
    Datuak
    -0.71
    SourceChecksum
    -0.71
    Vidite
    -0.68
     виправивши
    -0.66
    MessageOf
    -0.65
     Meksiku
    -0.65
    homonymie
    -0.61
     Мексичка
    -0.59
     beginnetje
    -0.59
    POSITIVE LOGITS
     in
    0.56
    ictured
    0.49
    UpInside
    0.49
     hausse
    0.48
     against
    0.47
    PURPOSE
    0.46
    Refreshing
    0.46
    laşı
    0.46
     createContext
    0.45
     généraux
    0.43
    Activations Density 3.560%

    No Known Activations