© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10232
    Prev
    Next
    INDEX
    Explanations

    the word "Saint" followed by a hyphen

    oai_token-act-pair · gemini-2.0-flash

    Saint

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    expandindo
    -0.94
     consultato
    -0.81
     виправивши
    -0.79
    InputBorder
    -0.76
     محفوظة
    -0.71
     informée
    -0.70
    الحياه
    -0.69
    reuung
    -0.69
     MainAxisSize
    -0.68
    QUIRY
    -0.68
    POSITIVE LOGITS
    ome
    0.41
     iprot
    0.40
    Hub
    0.40
    性
    0.39
    OuterClass
    0.38
    ôi
    0.37
     ملی
    0.37
     reste
    0.37
    V
    0.36
     bandas
    0.35
    Activations Density 0.099%

    No Known Activations