© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15471
    Prev
    Next
    INDEX
    Explanations

    lists of foodstuffs preceded by the word "of".

    oai_token-act-pair · 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
    Not in Any Lists

    No Comments

    Negative Logits
    dymyr
    -0.60
    IndentedString
    -0.53
    AutoresizingMask
    -0.52
    MessageOf
    -0.51
     auszu
    -0.51
     automatiques
    -0.50
    RegressionTest
    -0.50
    UpInside
    -0.49
     disponibilité
    -0.49
     verás
    -0.49
    POSITIVE LOGITS
    Portale
    0.72
    ViewFeatures
    0.60
    migrationBuilder
    0.59
     AssemblyCulture
    0.54
    djangoproject
    0.53
    strix
    0.53
     Lar
    0.53
     onOptions
    0.53
     numberOfRows
    0.52
     Corn
    0.51
    Activations Density 0.668%

    No Known Activations