© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12689
    Prev
    Next
    INDEX
    Explanations

    words ending in "ate", "ated", "ize", and "ized", as well as a couple of other related words.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     "..\..\..\
    -0.57
    IMPORTED
    -0.50
    jstor
    -0.49
     "..\..\
    -0.46
     Old
    -0.44
    llary
    -0.43
     <<<<<<<<<<<<<<
    -0.43
    javas
    -0.41
    reactivex
    -0.41
     Brown
    -0.41
    POSITIVE LOGITS
     themſelves
    0.87
     itſelf
    0.87
     myſelf
    0.85
     raiſ
    0.81
     fometimes
    0.81
     neceff
    0.74
     betweenstory
    0.73
     himſelf
    0.72
     Jefus
    0.72
    ſelves
    0.71
    Activations Density 2.512%

    No Known Activations