© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8622
    Prev
    Next
    INDEX
    Explanations

    the letters "J", "D", "O", "S", "Q", "L", and "C" in code and related computer language discussion

    oai_token-act-pair · gemini-2.0-flash

    terms related to programming, particularly Java

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

    Java Data Objects

    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
    脚注の使い方
    -0.65
    Einzelnachweise
    -0.56
     addObject
    -0.55
    ligen
    -0.53
     %>%
    -0.51
    andet
    -0.50
    VersionUID
    -0.50
    WebElementEntity
    -0.49
    AddHtmlAttribute
    -0.49
    eater
    -0.49
    POSITIVE LOGITS
    aarrggbb
    0.63
    bnf
    0.63
    GEBURTSDATUM
    0.57
    جغرافيا
    0.52
     bParam
    0.51
    PreferredItem
    0.51
    RequestMapping
    0.48
    rosh
    0.47
    ыгана
    0.46
    WillAppear
    0.46
    Activations Density 1.223%

    No Known Activations