© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15504
    Prev
    Next
    INDEX
    Explanations

    This neuron appears to activate on a mix of errors, indices, and the phrase "end of the".

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     فريبيس
    -0.93
     مرئيه
    -0.79
    RegressionTest
    -0.73
     समीक्षाओं
    -0.72
    tagHelperRunner
    -0.71
     Italijani
    -0.63
     CreateTagHelper
    -0.62
    Datuak
    -0.60
    脚注の使い方
    -0.59
     مشين
    -0.58
    POSITIVE LOGITS
    <h5>
    0.49
    kt
    0.49
    tencent
    0.48
        
    0.45
     kotor
    0.45
    <h4>
    0.45
    kkel
    0.43
    단
    0.43
    元
    0.43
    <table>
    0.42
    Activations Density 1.006%

    No Known Activations