© 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. 10335
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to activate on a wide variety of relatively common words in technical documents, regardless of the topic

    oai_token-act-pair · gemini-2.0-flash

    Academic papers

    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
     vertes
    -0.57
     planas
    -0.56
     blanches
    -0.54
     automatiques
    -0.51
     noires
    -0.48
     vectorielles
    -0.48
     sauvages
    -0.47
     habet
    -0.46
     réguli
    -0.45
     blancs
    -0.45
    POSITIVE LOGITS
     resourceCulture
    0.82
     Roskov
    0.78
    StoryboardSegue
    0.77
    InjectAttribute
    0.71
    ScopeManager
    0.71
    findpost
    0.70
    (!__
    0.70
    الإنجليزية
    0.69
     للاسماء
    0.69
     oprot
    0.68
    Activations Density 16.305%

    No Known Activations