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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 623
    Prev
    Next
    INDEX
    Explanations

    a mix of abstract section markers common in scientific papers

    oai_token-act-pair · gemini-2.0-flash

    periods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Ibarra
    -0.81
     Michelangelo
    -0.80
     Aguilera
    -0.78
     Hollis
    -0.78
    MigrationBuilder
    -0.77
     Schulte
    -0.76
     Schweitzer
    -0.76
     Marlowe
    -0.75
     Galbraith
    -0.75
     Cervantes
    -0.74
    POSITIVE LOGITS
     Descriptors
    0.39
     Folders
    0.32
    ytale
    0.31
     Fails
    0.31
    ,:);
    0.31
     Leaks
    0.31
     Datasets
    0.30
     Receipts
    0.30
     Ration
    0.29
     Quarters
    0.28
    Activations Density 16.756%

    No Known Activations