© 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. 7952
    Prev
    Next
    INDEX
    Explanations

    the letter "p" followed by other letters and symbols in computer code, and words related to the human body

    oai_token-act-pair · 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
    p
    -1.00
    ping
    -0.88
    ps
    -0.73
    pt
    -0.68
    ped
    -0.66
    pping
    -0.66
    pin
    -0.60
    pn
    -0.60
    psin
    -0.59
    ptest
    -0.59
    POSITIVE LOGITS
     MessageBoxIcon
    0.65
    GenerationType
    0.62
    Див
    0.57
    RenderAtEndOf
    0.57
    fortawesome
    0.57
     onPostExecute
    0.55
     Parad
    0.55
    onViewCreated
    0.53
     Partition
    0.53
    Subview
    0.53
    Activations Density 4.368%

    No Known Activations