© 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. 6365
    Prev
    Next
    INDEX
    Explanations

    words and phrases from baseball or other competitive sports contexts, often found in recaps or analyses

    oai_token-act-pair · gemini-2.0-flash

    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
     متعلقه
    -0.68
    adaptiveStyles
    -0.65
     fhort
    -0.64
     ſtate
    -0.60
     caufe
    -0.59
    contentLoaded
    -0.56
    NameInMap
    -0.54
     perfons
    -0.54
    Diweddarwch
    -0.54
     cauſe
    -0.53
    POSITIVE LOGITS
     ویکی‌پدیا
    0.52
    writeField
    0.48
     surla
    0.47
    رشف
    0.46
    InjectAttribute
    0.45
    EditorBrowsable
    0.45
    IVersion
    0.44
    Lähteet
    0.44
    IDAE
    0.44
    hyrchwyd
    0.44
    Activations Density 6.503%

    No Known Activations