© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2586
    Prev
    Next
    INDEX
    Explanations

    passages praising athletes and athletic achievement.

    oai_token-act-pair · gemini-2.0-flash

    Sports context

    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
     player
    -1.02
    player
    -0.94
     PLAYER
    -0.93
     Player
    -0.92
     soldier
    -0.90
     musician
    -0.89
     rider
    -0.89
     dancer
    -0.88
     athlete
    -0.86
     swimmer
    -0.86
    POSITIVE LOGITS
     disambiguazione
    0.58
    DataPropertyName
    0.56
    UpInside
    0.54
    GraphicsUnit
    0.50
    ALLENG
    0.47
    InstrumentedTest
    0.47
    ImageField
    0.47
    ValueStyle
    0.46
     للمعارف
    0.45
     UIApplication
    0.43
    Activations Density 2.971%

    No Known Activations