© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16155
    Prev
    Next
    INDEX
    Explanations

    C/C++ code snippets, particularly preprocessor directives and compiler-specific pragmas

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    TagMode
    -0.73
     وتسجيلات
    -0.66
    hages
    -0.60
     المعيارى
    -0.60
     AssemblyCulture
    -0.60
    Comté
    -0.60
    DockStyle
    -0.59
    ptid
    -0.58
    findpost
    -0.58
    tvguidetime
    -0.56
    POSITIVE LOGITS
     ROE
    0.49
     cantando
    0.48
     Walpole
    0.48
     mă
    0.47
     Più
    0.45
    @[
    0.45
     Pamphlet
    0.44
    ->___
    0.44
     Waffle
    0.44
     Waff
    0.43
    Activations Density 0.396%

    No Known Activations