© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14165
    Prev
    Next
    INDEX
    Explanations

    mathematical code and sports statistics, and words like "high," "best," or "most."

    oai_token-act-pair · gemini-2.0-flash

    maximum

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     betweenstory
    -0.85
    Personensuche
    -0.81
    躇
    -0.78
    RenderAtEndOf
    -0.75
     Reverso
    -0.71
     ddelweddau
    -0.69
     iprot
    -0.67
     initWithFrame
    -0.66
    ViewFeatures
    -0.65
     CreateTagHelper
    -0.64
    POSITIVE LOGITS
     max
    0.83
     Max
    0.78
     maximum
    0.75
    Max
    0.75
    max
    0.73
     MAX
    0.67
    MAX
    0.64
     Maximum
    0.62
     min
    0.58
    Maximum
    0.58
    Activations Density 1.324%

    No Known Activations