© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10338
    Prev
    Next
    INDEX
    Explanations

    soccer scores and game-related terms.

    oai_token-act-pair · gemini-2.0-flash

    Sports scores and dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     nakalista
    -0.57
     تضيفلها
    -0.56
     linkovi
    -0.56
    BeginContext
    -0.52
    ViewFeatures
    -0.48
    Clik
    -0.48
    ophageal
    -0.47
    Personendaten
    -0.46
    SourceChecksum
    -0.45
     мѣ
    -0.43
    POSITIVE LOGITS
     يتيمه
    0.65
     ddelweddau
    0.63
    counters
    0.63
     purpoſe
    0.61
    hassee
    0.61
     Counters
    0.60
     AOS
    0.60
    prü
    0.60
    MOC
    0.59
    vinas
    0.59
    Activations Density 4.580%

    No Known Activations