© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8102
    Prev
    Next
    INDEX
    Explanations

    code, especially related to tasks and file manipulation.

    oai_token-act-pair · gemini-2.0-flash

    code punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ValueStyle
    -0.83
     kasarigan
    -0.80
     CreateTagHelper
    -0.67
    MethodManager
    -0.66
    原始内容存档于
    -0.65
    SharedCtor
    -0.64
    verwijspagina
    -0.63
     AssemblyCulture
    -0.63
     ujednoznacz
    -0.62
    ArrowToggle
    -0.60
    POSITIVE LOGITS
    نه
    0.50
    亭
    0.47
    llis
    0.44
    TagMode
    0.44
    ftagPool
    0.44
     ahh
    0.43
    lüsse
    0.42
     plegable
    0.42
     enfin
    0.42
     rispetto
    0.41
    Activations Density 1.915%

    No Known Activations