© 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. 1637
    Prev
    Next
    INDEX
    Explanations

    C++ code related to reading extraction options

    oai_token-act-pair · gemini-2.0-flash

    Code or programming

    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
     making
    -1.16
     holding
    -1.13
     sharing
    -1.11
     writing
    -1.10
     teaching
    -1.09
     learning
    -1.09
     letting
    -1.09
     listening
    -1.07
     fixing
    -1.05
     running
    -1.04
    POSITIVE LOGITS
    elser
    0.50
     vulgaires
    0.50
     act
    0.48
     תע
    0.47
    ंदीखरीदारी
    0.46
     respond
    0.46
     eigen
    0.45
    jspx
    0.45
    AccessorTable
    0.45
     gerne
    0.44
    Activations Density 11.365%

    No Known Activations