© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9505
    Prev
    Next
    INDEX
    Explanations

    specific syntax elements related to string formatting and output in C-like languages, especially those involving "append" and format specifiers.

    oai_token-act-pair · gemini-2.0-flash

    String

    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
    Not in Any Lists

    No Comments

    Negative Logits
     sp
    -0.54
    őt
    -0.46
     co
    -0.44
    jno
    -0.43
     L
    -0.43
     hollow
    -0.42
    ὴν
    -0.42
    chium
    -0.41
    Sp
    -0.40
    ूत
    -0.39
    POSITIVE LOGITS
    invokeLater
    0.84
    makeConstraints
    0.79
    AddTagHelper
    0.73
    !*\
    0.73
    ReusableCell
    0.70
    webElementXpaths
    0.69
    sizeCache
    0.69
    BeginContext
    0.67
    saraba
    0.66
    ⓧ
    0.66
    Activations Density 1.464%

    No Known Activations