© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3981
    Prev
    Next
    INDEX
    Explanations

    terms related to Java, Maven, and software development, and also possibly the word "Rabbi"

    oai_token-act-pair · gemini-2.0-flash

    technical terms and code-related contexts

    np_token-act-pair-logits · gpt-4o-mini

    foreign language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    RefNanny
    -0.54
     I
    -0.43
    onade
    -0.40
    въ
    -0.39
    its
    -0.39
    SuppressMessage
    -0.36
    GIVEREF
    -0.36
    IBar
    -0.36
     въз
    -0.36
    AutoScale
    -0.35
    POSITIVE LOGITS
    انيف
    0.77
     endblock
    0.75
     RSSSF
    0.68
     Siamese
    0.67
     Kig
    0.67
    CreateModel
    0.65
     AppColors
    0.64
     Савезне
    0.63
    Conclusie
    0.62
     Beginnings
    0.61
    Activations Density 0.373%

    No Known Activations