© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6663
    Prev
    Next
    INDEX
    Explanations

    colon and quotation mark pairs

    oai_token-act-pair · gemini-2.0-flash

    :"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     myſelf
    -1.61
     uſed
    -1.54
     purpoſe
    -1.52
     itſelf
    -1.50
     pleaſure
    -1.45
     Jefus
    -1.40
     themſelves
    -1.39
     uſe
    -1.34
     fevere
    -1.34
    ſelf
    -1.33
    POSITIVE LOGITS
     [
    0.85
     ‘
    0.80
     Com
    0.75
     Ab
    0.75
     Col
    0.74
     et
    0.72
     V
    0.72
     Da
    0.72
     Th
    0.72
     a
    0.71
    Activations Density 0.476%

    No Known Activations