© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15655
    Prev
    Next
    INDEX
    Explanations

    code snippets with curly braces that are part of functions or blocks

    oai_token-act-pair · gemini-2.0-flash

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Geplaatst
    -0.61
    WebElementEntity
    -0.61
    Jeografia
    -0.59
    thenia
    -0.57
    rungsseite
    -0.56
    tvguidetime
    -0.56
    swire
    -0.54
     herv
    -0.54
     otomatig
    -0.54
    :✨
    -0.54
    POSITIVE LOGITS
    IUrlHelper
    0.49
    XmlAccessType
    0.46
    ivez
    0.45
    Solución
    0.43
    StoryboardSegue
    0.43
     nakalista
    0.42
    ябре
    0.41
     Plato
    0.41
    ImageContext
    0.40
     zufolge
    0.40
    Activations Density 0.110%

    No Known Activations