© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15538
    Prev
    Next
    INDEX
    Explanations

    information relating to legal and medical documents that contain figures

    oai_token-act-pair · gemini-2.0-flash

    say "The/First" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Искәрмәләр
    -0.67
    rungsseite
    -0.62
    Hozzáférés
    -0.58
    Cyfeiriadau
    -0.57
    AccessorTable
    -0.56
     AspNetCore
    -0.55
    Viitteet
    -0.54
     disambiguazione
    -0.53
    GenerationType
    -0.53
    Jeografia
    -0.49
    POSITIVE LOGITS
     Three
    1.89
     Third
    1.77
     Second
    1.77
     First
    1.72
     Two
    1.70
     Fourth
    1.68
     Four
    1.64
     Six
    1.63
     Five
    1.63
    Three
    1.61
    Activations Density 9.042%

    No Known Activations