© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9618
    Prev
    Next
    INDEX
    Explanations

    the substrings "ith" and "io", especially when they occur together, and sometimes "uchy" when it appears near "ith"

    oai_token-act-pair · 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
    Negative Logits
    ReusableCell
    -0.82
    醐
    -0.82
    StoryboardSegue
    -0.79
    новниш
    -0.78
     contextLoads
    -0.69
     trajets
    -0.69
     ujednoznacz
    -0.68
    AutoField
    -0.68
    sizeCache
    -0.68
    
    -0.67
    POSITIVE LOGITS
    edic
    0.64
    dit
    0.64
    dik
    0.61
    ditor
    0.59
    uatu
    0.58
     pinulongan
    0.57
    dic
    0.57
    dited
    0.56
    diti
    0.56
    di
    0.54
    Activations Density 0.252%

    No Known Activations