© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8822
    Prev
    Next
    INDEX
    Explanations

    code related to GUI buttons and views

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    tagHelperRunner
    -0.80
    +:+
    -0.79
    MigrationBuilder
    -0.78
     Italijanski
    -0.72
     дописавши
    -0.72
    ьаж
    -0.69
    queryInterface
    -0.67
    uxxxx
    -0.66
    SharedDtor
    -0.66
    \{\\
    -0.64
    POSITIVE LOGITS
     关闭
    0.47
    销毁
    0.46
     截图
    0.46
     上传
    0.46
    empereur
    0.44
    解锁
    0.44
    单击
    0.44
     跳转
    0.43
    触摸
    0.42
    onViewCreated
    0.42
    Activations Density 0.412%

    No Known Activations