© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13246
    Prev
    Next
    INDEX
    Explanations

    text describing inventions and their parts

    oai_token-act-pair · gemini-2.0-flash

    rod

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    人
    -0.58
     rod
    -0.55
     okazji
    -0.49
     rods
    -0.47
    enes
    -0.47
    rawQuery
    -0.47
    การ
    -0.46
     Anlass
    -0.46
    ene
    -0.45
    ines
    -0.44
    POSITIVE LOGITS
     propOrder
    1.02
     disambiguazione
    0.92
     surla
    0.86
     تضيفلها
    0.79
    RegistryLite
    0.79
    parsedMessage
    0.77
     الرياضيه
    0.77
     resourceCulture
    0.76
    曖昧さ回避
    0.76
     חיצוניים
    0.75
    Activations Density 5.357%

    No Known Activations