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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12172
    Prev
    Next
    INDEX
    Explanations

    Japanese and English words or phrases related to errors in Java and Maven projects

    oai_token-act-pair · gemini-2.0-flash

    errors in coding or implementation

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

    Code and other languages

    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
    BufferException
    -0.91
    SourceChecksum
    -0.88
    ViewImports
    -0.88
     purpoſe
    -0.83
     مشين
    -0.82
     Theſe
    -0.82
    TagMode
    -0.82
     كومونز
    -0.81
    elfth
    -0.80
    UnusedPrivate
    -0.80
    POSITIVE LOGITS
     kont
    0.47
     שנ
    0.36
    ola
    0.35
     RIS
    0.35
    Referències
    0.33
     تض
    0.33
     MongoDB
    0.32
    idd
    0.31
     متعلقه
    0.31
     به
    0.31
    Activations Density 0.199%

    No Known Activations