© 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. 10010
    Prev
    Next
    INDEX
    Explanations

    words that refer to people or groups of people

    oai_token-act-pair · gemini-2.0-flash

    People in specific roles

    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
    WriteTagHelper
    -0.73
     itſelf
    -0.70
     Efq
    -0.65
     Pergamon
    -0.65
     ALR
    -0.63
     gddr
    -0.63
     reaſon
    -0.62
     preſent
    -0.61
     useAppContext
    -0.60
     nephe
    -0.59
    POSITIVE LOGITS
     leaving
    0.70
     making
    0.66
     bringing
    0.64
     converting
    0.62
     taking
    0.62
     terminating
    0.60
     raising
    0.59
     retiring
    0.59
     coming
    0.59
     causing
    0.59
    Activations Density 1.933%

    No Known Activations