© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7167
    Prev
    Next
    INDEX
    Explanations

    locations in Canada, especially Toronto and Ottawa, and organizations like "Catholic" and "Knights".

    oai_token-act-pair · gemini-2.0-flash

    Toronto

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    pathic
    -0.46
    청
    -0.45
    serviceWorker
    -0.45
    nowrap
    -0.44
    掛け
    -0.44
     S
    -0.43
     Drop
    -0.42
    Ứ
    -0.42
     Ax
    -0.42
     drops
    -0.42
    POSITIVE LOGITS
    WriteLiteral
    0.70
    ViewImports
    0.66
     nakalista
    0.65
    Personendaten
    0.64
     Theſe
    0.62
    MigrationBuilder
    0.60
     Egli
    0.59
     GenerationType
    0.59
    BeforeMethod
    0.57
    Попис
    0.57
    Activations Density 0.569%

    No Known Activations