© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11438
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to American football (the NFL)

    oai_token-act-pair · gemini-2.0-flash

    American football

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     offense
    -0.57
     okuyayım
    -0.57
    RTDA
    -0.55
     Vrbo
    -0.53
    untura
    -0.53
     ComVisible
    -0.53
     '-':
    -0.52
     HttpNotFound
    -0.52
    ρον
    -0.51
     Horoscope
    -0.51
    POSITIVE LOGITS
     متعلقه
    0.73
     CreateTagHelper
    0.66
     فريبيس
    0.55
     spir
    0.44
     juguetes
    0.43
    estens
    0.43
     Naj
    0.43
    UnitId
    0.42
     Dav
    0.42
    utt
    0.41
    Activations Density 6.229%

    No Known Activations