© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2925
    Prev
    Next
    INDEX
    Explanations

    the prefix "mes", usually referring to the mesentery.

    oai_token-act-pair · gemini-2.0-flash

    mes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ViewImports
    -0.68
    MigrationBuilder
    -0.68
    WritableDatabase
    -0.66
    roek
    -0.65
     onCreateView
    -0.62
    хьтан
    -0.61
    StructEnd
    -0.61
    contentLoaded
    -0.59
    ObjectContext
    -0.59
    ometries
    -0.56
    POSITIVE LOGITS
    OGND
    0.50
     Jpa
    0.41
     ())
    0.40
     Hv
    0.39
    tadır
    0.39
     Exactos
    0.39
    twimg
    0.38
    jspb
    0.38
    entieth
    0.37
    acakt
    0.37
    Activations Density 0.492%

    No Known Activations