© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13783
    Prev
    Next
    INDEX
    Explanations

    This appears to be a very noisy neuron, but it seems to be primarily focused on verbs implying action, movement or change, along with a bias towards proper nouns, especially in Chinese.

    oai_token-act-pair · gemini-2.0-flash

    Shoes and foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ReusableCell
    -0.46
    تقاوى
    -0.43
     of
    -0.42
    invokeLater
    -0.42
     незавершена
    -0.41
    <!--[
    -0.40
    asmuch
    -0.40
     daß
    -0.40
    of
    -0.40
    ftagPool
    -0.40
    POSITIVE LOGITS
    SourceChecksum
    0.65
     panoramique
    0.61
    rogels
    0.58
    ConstraintMaker
    0.58
     cervello
    0.57
     benessere
    0.57
    localScale
    0.56
     médicale
    0.56
     boîte
    0.56
    letoe
    0.55
    Activations Density 10.586%

    No Known Activations