© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12223
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially those associated with organizations, laws, or religious topics

    oai_token-act-pair · gemini-2.0-flash

    Canon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    :✨
    -0.60
    didSet
    -0.56
    ={<
    -0.53
    parel
    -0.50
     uska
    -0.48
    igens
    -0.48
    hauer
    -0.48
    SpringBootTest
    -0.46
    %"
    -0.45
     uitgevoerd
    -0.43
    POSITIVE LOGITS
    Diwedd
    0.76
     nakalista
    0.72
     saites
    0.65
    رشف
    0.60
     Baillargeon
    0.60
     Curs
    0.59
     Riproduzione
    0.59
    Espèce
    0.58
    WebControls
    0.55
     démission
    0.55
    Activations Density 1.351%

    No Known Activations