© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14255
    Prev
    Next
    INDEX
    Explanations

    code-like text with a specific naming convention, potentially related to networking protocols

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    UVWXYZ
    -0.72
    — 
    -0.69
     Vo
    -0.68
    opress
    -0.68
     Na
    -0.66
    rateur
    -0.65
    iffance
    -0.65
     Stein
    -0.64
     Ba
    -0.64
    tlement
    -0.64
    POSITIVE LOGITS
     griega
    0.59
     enää
    0.58
     maail
    0.55
     hyö
    0.54
     näin
    0.54
     habet
    0.51
     sociala
    0.50
     kysy
    0.50
     grij
    0.48
     représ
    0.48
    Activations Density 2.844%

    No Known Activations