© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 11347
    Prev
    Next
    INDEX
    Explanations

    statistical numbers in sports articles, including points, averages, and rankings

    oai_token-act-pair · gemini-2.0-flash

    say "game"

    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
     Games
    -1.44
     games
    -1.40
    Games
    -1.34
    games
    -1.27
     GAMES
    -1.23
    GAMES
    -1.00
     Matches
    -0.86
     matches
    -0.85
     Spiele
    -0.84
     jeux
    -0.82
    POSITIVE LOGITS
    PerformLayout
    0.61
    Geographie
    0.56
     pinulongan
    0.56
    (!__
    0.55
     charters
    0.54
    لينكات
    0.53
    EXO
    0.52
     vouchers
    0.51
     pistons
    0.51
    reys
    0.50
    Activations Density 2.477%

    No Known Activations