© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1273
    Prev
    Next
    INDEX
    Explanations

    a mix of Russian and English terms related to website development and specifically the .htaccess file

    oai_token-act-pair · gemini-2.0-flash

    Code and 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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     inconvénients
    -0.51
     prochaines
    -0.48
     Giappone
    -0.48
     dernières
    -0.47
     għall
    -0.46
     vandens
    -0.45
    닥
    -0.45
     âmes
    -0.44
     pezzo
    -0.44
    깥
    -0.44
    POSITIVE LOGITS
    sizeCache
    0.69
    WriteBarrier
    0.62
    ValueStyle
    0.60
    HandlerContext
    0.57
    rrggbb
    0.57
    )=>{
    0.55
    Халык
    0.54
     >=",
    0.54
     ModelExpression
    0.52
    IsMutable
    0.52
    Activations Density 1.381%

    No Known Activations