© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8396
    Prev
    Next
    INDEX
    Explanations

    prepositions appearing in legal and historical documents

    oai_token-act-pair · gemini-2.0-flash

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     nonatomic
    -0.68
    yves
    -0.63
    uxxxx
    -0.60
    TagHelpers
    -0.58
    #
    -0.57
    országban
    -0.54
     MonoBehaviour
    -0.54
     fidèles
    -0.54
    enumi
    -0.53
     المعيارى
    -0.53
    POSITIVE LOGITS
    webElementXpaths
    0.63
    таратура
    0.52
    omitempty
    0.49
    verifyException
    0.49
    IUrlHelper
    0.48
     command
    0.47
    DeleteBehavior
    0.46
     endblock
    0.45
     Baillargeon
    0.45
     ";"
    0.43
    Activations Density 1.797%

    No Known Activations