© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 614
    Prev
    Next
    INDEX
    Explanations

    This neuron appears to activate on a wide variety of things including: file extensions, version numbers, code and percentages

    oai_token-act-pair · gemini-2.0-flash

    3

    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
    DoubleQuotes
    -0.94
    SequentialGroup
    -0.87
    oneofs
    -0.84
    ImageContext
    -0.84
    saraba
    -0.82
    openConnection
    -0.81
    endphp
    -0.74
     AssemblyCulture
    -0.72
    esModule
    -0.71
     myſelf
    -0.71
    POSITIVE LOGITS
    3
    1.42
     Three
    1.17
    ３
    1.09
    三
    1.05
     three
    1.05
    Three
    1.04
     THREE
    0.99
     三
    0.97
    THREE
    0.95
     ३
    0.94
    Activations Density 2.747%

    No Known Activations