© 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. 2362
    Prev
    Next
    INDEX
    Explanations

    proper nouns and numbers, especially those related to companies and locations

    oai_token-act-pair · gemini-2.0-flash

    plus, max

    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
     Monfieur
    -0.57
     spagno
    -0.56
     ProtoMessage
    -0.55
     quæ
    -0.52
     enfans
    -0.52
     Shakspeare
    -0.52
     Efq
    -0.50
     fermés
    -0.50
     nemici
    -0.50
     noDo
    -0.50
    POSITIVE LOGITS
     plus
    0.86
    plus
    0.86
     Plus
    0.85
     Select
    0.82
     max
    0.79
    Plus
    0.77
    select
    0.76
    max
    0.76
     Max
    0.76
     select
    0.76
    Activations Density 6.358%

    No Known Activations