© 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. 565
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to sports, particularly soccer, including leagues, championships, and game events.

    oai_token-act-pair · gemini-2.0-flash

    championships

    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
    はじめに
    -0.68
    featureID
    -0.63
     ligiloj
    -0.63
    ########.
    -0.60
     يتيمه
    -0.57
    fromnode
    -0.57
     noqa
    -0.56
     تضيفلها
    -0.55
    Izvori
    -0.54
    AutoField
    -0.53
    POSITIVE LOGITS
    OrBuilder
    0.61
     gawas
    0.58
     CreateTagHelper
    0.57
    writeObject
    0.50
    rentino
    0.50
    นะคะ
    0.49
    NOPQRST
    0.48
    neth
    0.48
    vielen
    0.47
    oat
    0.47
    Activations Density 4.557%

    No Known Activations