© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9866
    Prev
    Next
    INDEX
    Explanations

    percent encoded characters in URLs

    oai_token-act-pair · gemini-2.0-flash

    2

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     الحره
    -0.62
    scriptId
    -0.59
    MethodManager
    -0.53
    tencent
    -0.51
    ArgumentParser
    -0.50
    reicher
    -0.49
    yyj
    -0.47
     xo
    -0.47
    sac
    -0.46
    SupportActionBar
    -0.46
    POSITIVE LOGITS
     referenties
    0.72
    expandindo
    0.66
    HtmlAttribute
    0.59
     culturelles
    0.57
     للاسماء
    0.56
     AssemblyCulture
    0.54
    喱
    0.54
     للمعارف
    0.54
    GEBURTS
    0.53
    XMLSchema
    0.52
    Activations Density 0.760%

    No Known Activations