© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1581
    Prev
    Next
    INDEX
    Explanations

    words related to sports and games.

    oai_token-act-pair · gemini-2.0-flash

    Sports upsets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     المعيارى
    -0.84
     Efq
    -0.79
     surla
    -0.78
    PreferredItem
    -0.75
    mặt
    -0.68
    InvalidProtocol
    -0.68
    balleur
    -0.66
    getColumnIndex
    -0.65
    mybatisplus
    -0.64
     SqlCommand
    -0.64
    POSITIVE LOGITS
     match
    0.47
     initComponents
    0.44
    match
    0.42
    Match
    0.42
     vis
    0.42
    MergeFrom
    0.42
    entis
    0.41
     kohta
    0.40
     komple
    0.40
    IsContent
    0.39
    Activations Density 0.548%

    No Known Activations