© 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. 975
    Prev
    Next
    INDEX
    Explanations

    various syntax elements from programming languages.

    oai_token-act-pair · gemini-2.0-flash

    code parsing/compiling

    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
     “
    -1.60
    ,”
    -1.50
     ‘
    -1.45
     ""
    -1.39
    .”
    -1.39
    ”,
    -1.38
    ”.
    -1.34
    、“
    -1.34
    ?”
    -1.34
     (“
    -1.33
    POSITIVE LOGITS
     Jefus
    0.73
     pleaſure
    0.72
     itſelf
    0.70
     himſelf
    0.68
    ſelf
    0.66
     myſelf
    0.66
     ſta
    0.66
     ſte
    0.66
     purpoſe
    0.65
     leaſt
    0.64
    Activations Density 2.198%

    No Known Activations