© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7983
    Prev
    Next
    INDEX
    Explanations

    instances of scientific or mathematical discussion, especially those involving symbols, units, and possibly citations

    oai_token-act-pair · gemini-2.0-flash

    sim

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     compared
    -0.48
     his
    -0.46
     
    -0.46
     "
    -0.45
     rispetto
    -0.43
    ter
    -0.42
     dibanding
    -0.42
    man
    -0.42
    og
    -0.41
     nor
    -0.41
    POSITIVE LOGITS
     betweenstory
    1.32
     itſelf
    1.16
     myſelf
    1.13
    MigrationBuilder
    1.09
     ſeveral
    1.08
     purpoſe
    1.01
     Theſe
    0.96
     pleaſure
    0.95
     themſelves
    0.94
     Efq
    0.92
    Activations Density 1.479%

    No Known Activations