© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11400
    Prev
    Next
    INDEX
    Explanations

    code blocks, specifically the characters, keywords, and variable names commonly found in C++ and Python code.

    oai_token-act-pair · gemini-2.0-flash

    n

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    n
    -0.55
    f
    -0.55
     académica
    -0.52
    d
    -0.51
     giấc
    -0.51
    łości
    -0.49
     Inscrivez
    -0.47
    Advertisement
    -0.47
    htë
    -0.47
    is
    -0.47
    POSITIVE LOGITS
     externi
    0.69
     propOrder
    0.66
     للاسماء
    0.65
     تضيفلها
    0.64
     surla
    0.57
    Enllaces
    0.54
     OMITBAD
    0.54
    Personensuche
    0.53
    SourceChecksum
    0.53
    Билгалдахарш
    0.52
    Activations Density 3.994%

    No Known Activations