© 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. 2753
    Prev
    Next
    INDEX
    Explanations

    this neuron seems to activate when it finds a verb ending in 'ts', science terms, and the string '&'.

    oai_token-act-pair · gemini-2.0-flash

    sugges

    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
    WebElementEntity
    -0.65
     تعدى
    -0.54
    SerializeField
    -0.50
     تانيه
    -0.50
    مصادر
    -0.49
    şiv
    -0.48
    endis
    -0.48
    orius
    -0.47
    alek
    -0.47
    zon
    -0.47
    POSITIVE LOGITS
    ns
    0.91
    ts
    0.90
    ls
    0.87
    bs
    0.87
     propOrder
    0.85
    ps
    0.83
    ms
    0.81
     ns
    0.78
    ds
    0.75
    gs
    0.71
    Activations Density 6.714%

    No Known Activations