© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7259
    Prev
    Next
    INDEX
    Explanations

    the phrase "make sense"

    oai_token-act-pair · gemini-2.0-flash

    make

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    IActionResult
    -0.56
     feeling
    -0.51
    رشف
    -0.47
     onCancelled
    -0.46
    RunWith
    -0.44
     felt
    -0.43
     Feeling
    -0.42
    feeling
    -0.42
    scalatest
    -0.42
    Feeling
    -0.42
    POSITIVE LOGITS
     surla
    0.69
    transQ
    0.68
    uride
    0.67
    PreferredItem
    0.66
    ########.
    0.65
    orithmic
    0.65
     linkovi
    0.65
     Roskov
    0.64
     Paused
    0.62
    ViewImports
    0.60
    Activations Density 0.581%

    No Known Activations