© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13392
    Prev
    Next
    INDEX
    Explanations

    information about tennis tournaments, particularly the Australian Open in 1996

    oai_token-act-pair · gemini-2.0-flash

    Code and sports articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    DrawerToggle
    -0.57
     оригіналу
    -0.57
    webElementXpaths
    -0.56
    nosaurus
    -0.56
     ILogger
    -0.55
     Eichen
    -0.55
    hadores
    -0.54
    Coordonnées
    -0.54
     Bunk
    -0.54
     समीक्षक
    -0.54
    POSITIVE LOGITS
    featureID
    0.53
    mobileqq
    0.49
    ficult
    0.48
     dụ
    0.42
    WriteHeader
    0.42
     робота
    0.41
     собою
    0.41
    tetten
    0.41
    oretical
    0.40
    meralda
    0.40
    Activations Density 1.550%

    No Known Activations