© 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. 7360
    Prev
    Next
    INDEX
    Explanations

    capital letters appearing in unusual contexts

    oai_token-act-pair · gemini-2.0-flash

    Italian place names

    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
    зу
    -0.51
    veu
    -0.41
     exp
    -0.39
     fij
    -0.39
     double
    -0.39
     triple
    -0.38
    uki
    -0.38
    べき
    -0.37
    ')){
    -0.37
     habit
    -0.37
    POSITIVE LOGITS
    MLLoader
    0.99
    ConstraintMaker
    0.99
    AddTagHelper
    0.93
    IntoConstraints
    0.90
     <>",
    0.83
     ModelExpression
    0.81
    ThroughAttribute
    0.79
     AssemblyCulture
    0.74
     transfieras
    0.73
    TypedDataSet
    0.72
    Activations Density 0.196%

    No Known Activations