© 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. 13390
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to sports, expecially regarding skills and practice

    oai_token-act-pair · gemini-2.0-flash

    basketball

    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
    ArrowToggle
    -0.69
     Infórmanos
    -0.62
    criminator
    -0.60
     iprot
    -0.54
     practiced
    -0.54
     Wikiseite
    -0.53
     Cartel
    -0.50
     hierogly
    -0.50
    ViewFeatures
    -0.50
    "],
    -0.50
    POSITIVE LOGITS
     strikes
    0.55
     field
    0.55
    AnchorStyles
    0.53
    tadi
    0.52
    ContainsKey
    0.52
    Obrázky
    0.50
    abstractmethod
    0.50
     saves
    0.48
     strike
    0.47
     reads
    0.47
    Activations Density 2.989%

    No Known Activations