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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11975
    Prev
    Next
    INDEX
    Explanations

    words and code snippets from software development, especially related to database operations, UI elements and legal documents

    oai_token-act-pair · gemini-2.0-flash

    computer code and database records

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     
    -0.54
    CrossRef
    -0.50
    ↵
    -0.49
    ever
    -0.49
     en
    -0.48
     “
    -0.44
     in
    -0.44
     ever
    -0.43
    mer
    -0.42
    #+#
    -0.42
    POSITIVE LOGITS
     Efq
    0.98
    RectangleBorder
    0.95
    findpost
    0.91
    uxxxx
    0.88
     CreateTagHelper
    0.87
    InputBorder
    0.86
     étoit
    0.84
     Monfieur
    0.84
     ainfi
    0.84
    存于互联网档案馆
    0.83
    Activations Density 3.786%

    No Known Activations