© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13920
    Prev
    Next
    INDEX
    Explanations

    the word "pie" (and sometimes "the") in a document

    oai_token-act-pair · gemini-2.0-flash

    pie

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ^(@)
    -2.11
     Theſe
    -1.96
    ſelf
    -1.94
     myſelf
    -1.93
     Efq
    -1.91
    ſelves
    -1.90
     itſelf
    -1.85
     greateſt
    -1.83
     purpoſe
    -1.80
     Jefus
    -1.80
    POSITIVE LOGITS
    ↵↵
    1.41
    <bos>
    1.32
    1
    1.22
    ↵
    1.20
    2
    1.19
    I
    1.15
    '
    1.13
     
    1.08
    0
    1.06
    -
    1.06
    Activations Density 0.645%

    No Known Activations