© 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. 14377
    Prev
    Next
    INDEX
    Explanations

    descriptions of Malay and Indonesian food dishes

    oai_token-act-pair · gemini-2.0-flash

    Indonesian food and scientific 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
    SharedDtor
    -0.56
    writeFieldEnd
    -0.52
     Null
    -0.52
    queryInterface
    -0.50
    ="@+
    -0.50
    LoadScene
    -0.49
     astore
    -0.47
     null
    -0.46
    obj
    -0.46
    jka
    -0.46
    POSITIVE LOGITS
    InSection
    0.77
     EconPapers
    0.67
    ParallelGroup
    0.60
    Lähteet
    0.60
    URLException
    0.58
     jäsen
    0.57
     VIDEOTAPE
    0.56
     chrétienne
    0.53
     sirena
    0.52
     виправивши
    0.52
    Activations Density 0.508%

    No Known Activations