© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10031
    Prev
    Next
    INDEX
    Explanations

    polite forms of address to royalty

    oai_token-act-pair · gemini-2.0-flash

    possessive pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    OGND
    -1.09
     chng
    -0.82
     himo
    -0.75
    afficheront
    -0.74
    addContainerGap
    -0.73
    NameInMap
    -0.71
     transfieras
    -0.71
    BagConstraints
    -0.71
    ագրություններ
    -0.71
    AccessorTable
    -0.71
    POSITIVE LOGITS
    Personendaten
    0.43
     
    0.40
     AM
    0.39
     net
    0.39
     both
    0.38
    ding
    0.38
     this
    0.37
     nor
    0.36
    D
    0.36
     $\
    0.35
    Activations Density 0.581%

    No Known Activations