© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10046
    Prev
    Next
    INDEX
    Explanations

    measurements in inches or millimeters, often referring to sizes of components.

    oai_token-act-pair · gemini-2.0-flash

    "

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ագրություններ
    -0.69
    ñan
    -0.50
     Вікіпе
    -0.48
     resourceCulture
    -0.44
     consultato
    -0.44
    DockStyle
    -0.43
    ář
    -0.43
     initComponents
    -0.43
    uaire
    -0.42
     détach
    -0.42
    POSITIVE LOGITS
    Personensuche
    0.73
     JScrollPane
    0.63
    autique
    0.63
    SBATCH
    0.62
     propOrder
    0.57
     vine
    0.57
    JsonInclude
    0.57
    colos
    0.56
    Autoritní
    0.56
    ειν
    0.55
    Activations Density 3.889%

    No Known Activations