© 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. 14423
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming-related terms.

    oai_token-act-pair · gemini-2.0-flash

    underscore

    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
     Then
    -0.70
     للاسماء
    -0.70
     We
    -0.70
     rempliss
    -0.69
     Also
    -0.68
     Finally
    -0.68
    writeFieldEnd
    -0.68
     répar
    -0.68
     متعلقه
    -0.68
     rechange
    -0.66
    POSITIVE LOGITS
    SupportActionBar
    0.51
     planets
    0.45
     islands
    0.45
     constellations
    0.44
     island
    0.43
     fundamentals
    0.43
     planet
    0.43
     symbols
    0.43
     elements
    0.42
     prism
    0.42
    Activations Density 1.991%

    No Known Activations