© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9429
    Prev
    Next
    INDEX
    Explanations

    the word "que" in a Spanish context and some French as well

    oai_token-act-pair · gemini-2.0-flash

    que

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    TagHelper
    -0.76
    yntaxException
    -0.76
    CodeAttribute
    -0.62
     disambiguazione
    -0.58
    Diwedd
    -0.56
    InjectAttribute
    -0.56
    HasAnnotation
    -0.55
    què
    -0.54
    GTCX
    -0.54
    PendingIntent
    -0.54
    POSITIVE LOGITS
     فريبيس
    0.55
    épend
    0.54
     Solano
    0.53
    綜合報導
    0.52
    abestanden
    0.51
    transQ
    0.48
    שוב
    0.48
    èlement
    0.47
    Person
    0.47
    mbia
    0.47
    Activations Density 0.569%

    No Known Activations