© 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. 10284
    Prev
    Next
    INDEX
    Explanations

    place names, countries, and ethnicities, particularly in Central America, Africa, and associated with slavery

    oai_token-act-pair · gemini-2.0-flash

    Country/region names

    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
    Personendaten
    -1.12
    ArgsConstructor
    -1.06
    RegressionTest
    -1.05
    AndEndTag
    -1.02
    InjectAttribute
    -1.00
    tvguidetime
    -0.97
     typelib
    -0.96
    #+#
    -0.94
    webElementXpaths
    -0.93
    Personensuche
    -0.91
    POSITIVE LOGITS
     ſtand
    0.48
     uſed
    0.48
     Efq
    0.48
     uſe
    0.42
    cer
    0.40
     Houſe
    0.39
     siè
    0.39
     universitario
    0.38
     paſſ
    0.38
     miſ
    0.37
    Activations Density 4.084%

    No Known Activations