© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4961
    Prev
    Next
    INDEX
    Explanations

    lines of code that import libraries or packages

    oai_token-act-pair · gemini-2.0-flash

    Android code

    np_max-act-logits · 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
     Prescott
    -0.58
    Einzelnachweise
    -0.57
    ordinaire
    -0.57
    原始内容存档于
    -0.57
     مشين
    -0.52
     */;
    -0.52
    .*")]
    -0.50
     preponderance
    -0.50
    Források
    -0.49
     discomfort
    -0.49
    POSITIVE LOGITS
    AddHtmlAttribute
    0.86
     onAnimation
    0.84
    TagMode
    0.79
    stateProvider
    0.74
    textTheme
    0.72
    invokeLater
    0.68
    sidemargin
    0.66
    XmlAccessType
    0.65
    SuppressLint
    0.64
     NSCoder
    0.63
    Activations Density 2.400%

    No Known Activations