© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14053
    Prev
    Next
    INDEX
    Explanations

    This neuron appears to activate on code snippets and user interface elements, possibly related to web development or specific coding languages

    oai_token-act-pair · gemini-2.0-flash

    non-English

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     poitrine
    -0.50
     îna
    -0.49
    codegen
    -0.49
     împre
    -0.48
     secco
    -0.47
     Mexicano
    -0.46
     AssemblyCompany
    -0.46
     maș
    -0.45
     reven
    -0.45
    StartCoroutine
    -0.44
    POSITIVE LOGITS
    ंदीखरीदारी
    0.65
    PerformLayout
    0.65
    Personendaten
    0.64
     AssemblyCulture
    0.60
     }}"></
    0.60
     lenker
    0.60
     getC
    0.59
     cla
    0.59
    tagHelperRunner
    0.58
     урна
    0.58
    Activations Density 1.276%

    No Known Activations