© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15391
    Prev
    Next
    INDEX
    Explanations

    mentions of athletic clothing brands, specifically Under Armour and Gameness

    oai_token-act-pair · gemini-2.0-flash

    athletic wear product descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     المعيارى
    -0.45
     getItemCount
    -0.43
    GIVEREF
    -0.42
     adota
    -0.42
    öhe
    -0.41
     navires
    -0.41
     compless
    -0.40
    WaitGroup
    -0.40
     diber
    -0.40
    minecraftforge
    -0.39
    POSITIVE LOGITS
     ―――――
    0.66
    queryInterface
    0.65
     seams
    0.64
    ContentAlignment
    0.64
    ſelf
    0.63
    ArrowToggle
    0.63
     Waray
    0.63
     Theſe
    0.62
     fabrics
    0.60
    stdc
    0.59
    Activations Density 4.310%

    No Known Activations