© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9735
    Prev
    Next
    INDEX
    Explanations

    the word "per se" or stems of the word "permanent"

    oai_token-act-pair · gemini-2.0-flash

    per se

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     typelib
    -0.77
    ]")]
    -0.67
     Infórmanos
    -0.62
    }');
    -0.61
    ]';
    -0.61
    MemoryWarning
    -0.60
    httphttps
    -0.59
     peric
    -0.59
    RegistryLite
    -0.59
    InputBorder
    -0.59
    POSITIVE LOGITS
    selaer
    0.50
    Хьажоргаш
    0.48
     ":"
    0.46
    restre
    0.45
    лька
    0.43
    :✨
    0.43
     către
    0.43
    KeyDown
    0.43
    edores
    0.42
     rígida
    0.42
    Activations Density 0.358%

    No Known Activations