© 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. 10042
    Prev
    Next
    INDEX
    Explanations

    words, letter combinations, and abbreviations from the Malay language

    oai_token-act-pair · gemini-2.0-flash

    web pages

    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
    MigrationBuilder
    -0.88
    AccessorTable
    -0.81
    rungsseite
    -0.80
    ագրություններ
    -0.79
     referenties
    -0.75
    хьтан
    -0.75
    FunctionFlags
    -0.74
    OGND
    -0.73
    MLLoader
    -0.71
    /**
    -0.71
    POSITIVE LOGITS
     para
    0.40
     LITERATURE
    0.38
    sk
    0.37
    f
    0.37
     пое
    0.36
     Vign
    0.36
     tema
    0.36
    setupUi
    0.35
     je
    0.35
     hu
    0.34
    Activations Density 0.365%

    No Known Activations