© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13021
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to sports, particularly soccer teams and game statistics.

    oai_token-act-pair · gemini-2.0-flash

    Sports and games

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    AddTagHelper
    -0.82
     AssemblyCulture
    -0.73
    GEBURTSDATUM
    -0.61
    adaptiveStyles
    -0.55
    ORPG
    -0.51
    <bos>
    -0.51
     Paglinawan
    -0.51
     Վերցված
    -0.50
    rylic
    -0.49
     Drapeau
    -0.49
    POSITIVE LOGITS
    MessageTagHelper
    0.66
    onAttach
    0.65
    onViewCreated
    0.64
     educativos
    0.58
    wpi
    0.55
    ReusableCell
    0.51
     deportivos
    0.51
    Література
    0.50
    acijos
    0.49
    Життєпис
    0.49
    Activations Density 2.228%

    No Known Activations