© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 8591
    Prev
    Next
    INDEX
    Explanations

    something (The behavior of this neuron is too complex to summarize accurately in a single sentence.)

    oai_token-act-pair · gemini-2.0-flash

    German and English text

    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
    setopt
    -0.59
     Rowe
    -0.47
    Marshaller
    -0.45
     TAMBÉM
    -0.43
    Dichloroethene
    -0.42
     CURLOPT
    -0.42
    Климат
    -0.41
     Extra
    -0.41
    Management
    -0.41
    LError
    -0.40
    POSITIVE LOGITS
    AccessorTable
    0.90
    UseVisualStyle
    0.70
    setVerticalGroup
    0.65
     kaynağından
    0.63
    expandindo
    0.60
    MethodManager
    0.57
    例文帳に追加
    0.56
    umber
    0.54
    writeFieldEnd
    0.54
    piram
    0.54
    Activations Density 0.485%

    No Known Activations