© 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. 10101
    Prev
    Next
    INDEX
    Explanations

    programming code and possibly currency symbols, especially in JSON or other structured text formats

    oai_token-act-pair · gemini-2.0-flash

    Code and 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_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
    setVerticalGroup
    -0.66
    PyExc
    -0.60
     فريبيس
    -0.60
    CHN
    -0.59
     nahilalakip
    -0.59
    الإنجليزية
    -0.59
    mapStateToProps
    -0.58
     CN
    -0.58
    ViewImports
    -0.57
     wireType
    -0.56
    POSITIVE LOGITS
    l
    0.54
    f
    0.49
    どり
    0.48
    ie
    0.47
    c
    0.46
     CURLOPT
    0.46
    g
    0.45
    lt
    0.45
    um
    0.44
     Dungeon
    0.44
    Activations Density 0.596%

    No Known Activations