© 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. 10066
    Prev
    Next
    INDEX
    Explanations

    language related to American football

    oai_token-act-pair · gemini-2.0-flash

    sports offseason program

    np_max-act · gemini-2.0-flash

    offseason

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    verwijspagina
    -0.60
     BaseController
    -0.57
    gonic
    -0.56
     '{@
    -0.56
    tagext
    -0.55
     getCode
    -0.55
    deviantart
    -0.55
    sizePolicy
    -0.54
     ***!
    -0.53
     setCode
    -0.53
    POSITIVE LOGITS
     offseason
    0.75
    Портал
    0.58
     longe
    0.50
    MLLoader
    0.48
     hire
    0.48
    jws
    0.47
     preseason
    0.47
    rila
    0.45
    viewDidLoad
    0.44
     Biôgrafia
    0.44
    Activations Density 0.829%

    No Known Activations