© 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. 10255
    Prev
    Next
    INDEX
    Explanations

    the word "lead" and words closely associated with it

    oai_token-act-pair · gemini-2.0-flash

    lead

    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
    MLLoader
    -0.65
    StoryboardSegue
    -0.53
     createSlice
    -0.46
     far
    -0.45
     Leader
    -0.42
     lead
    -0.41
     líder
    -0.39
     Ch
    -0.39
     ch
    -0.38
     os
    -0.38
    POSITIVE LOGITS
     ویکی‌پدیا
    1.07
     يتيمه
    0.87
    rrggbb
    0.82
    Geplaatst
    0.82
    GEBURTSDATUM
    0.76
     TAMBÉM
    0.73
     Infórmanos
    0.73
     alluminio
    0.70
    Rujuakan
    0.69
     تضيفلها
    0.69
    Activations Density 0.872%

    No Known Activations