© 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. 4585
    Prev
    Next
    INDEX
    Explanations

    Javascript code, particularly related to object properties and math functions, as well as the keyword "box"

    oai_token-act-pair · gemini-2.0-flash

    Code, mixed text

    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
    脚注の使い方
    -0.89
    mybatisplus
    -0.71
    balleur
    -0.69
    ंदीखरीदारी
    -0.68
    JTable
    -0.65
    ьаж
    -0.63
    Obrázky
    -0.62
     defStyle
    -0.60
     ddelweddau
    -0.60
    цездатний
    -0.59
    POSITIVE LOGITS
    igshid
    0.48
    9
    0.47
     nine
    0.45
     nueve
    0.42
     Bau
    0.41
    parametrize
    0.41
     девя
    0.40
    lawan
    0.39
    外部链接
    0.38
     Nine
    0.37
    Activations Density 0.081%

    No Known Activations