© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2409
    Prev
    Next
    INDEX
    Explanations

    what appears to be inconsistent, but the neuron seems strongly activated by Japanese words in a particular context.

    oai_token-act-pair · gemini-2.0-flash

    Different languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Re
    -0.42
    CodeAttribute
    -0.41
    inaires
    -0.38
    re
    -0.38
     Mann
    -0.37
    existsSync
    -0.35
    Fol
    -0.35
    Do
    -0.35
    Портал
    -0.35
    DO
    -0.34
    POSITIVE LOGITS
    XmlAccessType
    0.66
    alyptus
    0.61
    TypedDataSet
    0.60
    ंदीखरीदारी
    0.59
    noid
    0.58
     الدولى
    0.58
    تفصیلات
    0.57
    เฉ
    0.57
     Predic
    0.57
     neem
    0.57
    Activations Density 0.233%

    No Known Activations