© 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. 9258
    Prev
    Next
    INDEX
    Explanations

    This neuron appears to activate on various seemingly unrelated tokens, possibly indicating a complex pattern or multiple sub-patterns

    oai_token-act-pair · gemini-2.0-flash

    2

    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
    ⓧ
    -0.74
     Italijanski
    -0.74
    HomeAsUpEnabled
    -0.73
    featureID
    -0.71
     CreateTagHelper
    -0.71
    WebVitals
    -0.68
     لينك
    -0.68
     createState
    -0.66
    ="@+
    -0.66
     ProtoMessage
    -0.66
    POSITIVE LOGITS
    2
    1.73
     twenty
    1.17
    ２
    1.15
     Twenty
    1.09
     TWENTY
    0.91
    ২
    0.91
    Twenty
    0.87
    २
    0.86
     ٢
    0.85
     ۲
    0.83
    Activations Density 6.474%

    No Known Activations