© 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. 9477
    Prev
    Next
    INDEX
    Explanations

    units of measurement and words surrounding them in scientific studies

    oai_token-act-pair · gemini-2.0-flash

    /

    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
     Ket
    -1.05
     Kir
    -1.02
     Kernel
    -1.02
     Ker
    -1.02
     Kelly
    -1.02
     Kenny
    -1.01
     Keyword
    -1.00
     Kenney
    -1.00
    Ket
    -0.99
    Kernel
    -0.96
    POSITIVE LOGITS
    𝙠
    0.48
     propOrder
    0.47
    𝘬
    0.47
     vuonna
    0.45
    unmodifiable
    0.44
     Draper
    0.43
    SimpleDateFormat
    0.42
    ρης
    0.42
    StoreMessageInfo
    0.42
    ㅤ
    0.41
    Activations Density 1.338%

    No Known Activations