© 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. 588
    Prev
    Next
    INDEX
    Explanations

    code-related text, specifically programming syntax and coding terms

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
     __
    -1.88
    (_
    -1.77
     ________
    -1.74
     ____
    -1.73
     (_
    -1.68
     _
    -1.66
     _____
    -1.66
     ___
    -1.64
     _______
    -1.62
     ______
    -1.61
    POSITIVE LOGITS
    SharedDtor
    0.71
    Enllaces
    0.63
    saraba
    0.62
    Geografi
    0.59
     للمعارف
    0.54
     AttributeSet
    0.52
    RTCK
    0.52
    MemoryWarning
    0.51
    CppMethod
    0.50
    BufferException
    0.49
    Activations Density 3.216%

    No Known Activations