© 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. 10269
    Prev
    Next
    INDEX
    Explanations

    geographical placenames, specifically towns and regions in certain parts of the world, with a bias for names ending in certain suffixes

    oai_token-act-pair · gemini-2.0-flash

    Non-English text

    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
    featureID
    -0.81
    ########.
    -0.77
     kaynağından
    -0.76
    BeginContext
    -0.75
    ConstraintMaker
    -0.73
    SharedDtor
    -0.72
    __':
    -0.66
    IndentedString
    -0.63
    TestBed
    -0.61
     nahilalakip
    -0.61
    POSITIVE LOGITS
    ,
    0.47
     sportifs
    0.42
     käytet
    0.40
    området
    0.38
    .
    0.38
     périph
    0.36
     gyakor
    0.36
     invloed
    0.36
     anhyd
    0.36
     quartiere
    0.36
    Activations Density 1.276%

    No Known Activations