© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1434
    Prev
    Next
    INDEX
    Explanations

    prepositions and relational terms used in scientific writing

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     intptr
    -0.57
    CJK
    -0.53
    rzost
    -0.49
    bkz
    -0.48
    ändig
    -0.48
    合
    -0.47
    olutamente
    -0.47
     klikken
    -0.47
    kary
    -0.46
    komend
    -0.45
    POSITIVE LOGITS
     pleaſure
    0.91
     ſeveral
    0.81
     himſelf
    0.76
     myſelf
    0.74
     ſever
    0.73
    ſelves
    0.72
     greateſt
    0.70
    ſelf
    0.70
     itſelf
    0.70
     leaſt
    0.69
    Activations Density 2.375%

    No Known Activations