© 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. 10070
    Prev
    Next
    INDEX
    Explanations

    names of people and movies

    oai_token-act-pair · gemini-2.0-flash

    movies and plays

    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
    inquirer
    -0.57
    Werke
    -0.57
     MaterialApp
    -0.53
    querque
    -0.50
     getM
    -0.49
    Personendaten
    -0.49
    mappedBy
    -0.49
     Land
    -0.48
     dial
    -0.48
     comma
    -0.48
    POSITIVE LOGITS
     >=",
    0.62
    expandindo
    0.60
     Athen
    0.59
     للاسماء
    0.59
     vPvB
    0.56
    RegressionTest
    0.53
     تانيه
    0.53
     Ingrid
    0.52
     Monaghan
    0.51
     SQLITE
    0.50
    Activations Density 2.570%

    No Known Activations