© 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. 10265
    Prev
    Next
    INDEX
    Explanations

    opinionated language and logical argumentation

    oai_token-act-pair · gemini-2.0-flash

    Be verb

    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
     diritti
    -0.45
    śla
    -0.45
    hoch
    -0.44
     textStatus
    -0.44
    RectangleBorder
    -0.44
     rä
    -0.43
     collectie
    -0.43
     medidor
    -0.43
     kvad
    -0.43
     precedentes
    -0.42
    POSITIVE LOGITS
    twimg
    0.79
    NameInMap
    0.72
    ContentAsync
    0.70
    ScopeManager
    0.66
     disputed
    0.65
    ⓘ
    0.64
    CopyWith
    0.64
     autorytatywna
    0.62
     beset
    0.61
     illusory
    0.60
    Activations Density 2.311%

    No Known Activations