© 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. 15333
    Prev
    Next
    INDEX
    Explanations

    the word "Man" followed by a noun

    oai_token-act-pair · gemini-2.0-flash

    man

    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
    تقاوى
    -0.61
     bezeichneter
    -0.55
     препратки
    -0.52
     NSCoder
    -0.48
     EconPapers
    -0.48
    StoreMessageInfo
    -0.47
     transfieras
    -0.47
    GEBURTSDATUM
    -0.47
     >=",
    -0.47
     समीक्षाओं
    -0.43
    POSITIVE LOGITS
    ifoli
    0.56
    abilia
    0.56
    ifolium
    0.55
    zini
    0.51
    DNEY
    0.51
    çais
    0.51
    hauer
    0.50
    tils
    0.50
    ikar
    0.50
    nonatomic
    0.49
    Activations Density 4.945%

    No Known Activations