© 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
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 15433
    Prev
    Next
    INDEX
    Explanations

    text with lots of punctuation and references to years, locations and professions.

    oai_token-act-pair · gemini-2.0-flash

    life

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     you
    -0.94
     ourselves
    -0.85
    you
    -0.81
     myſelf
    -0.75
     CreateTagHelper
    -0.73
     oneself
    -0.68
     Bourgoin
    -0.67
    CrossRef
    -0.67
    You
    -0.66
     Você
    -0.65
    POSITIVE LOGITS
     trekken
    0.53
     he
    0.52
     <<<<<<<<<<<<<<
    0.51
     LoggerFactory
    0.47
     useCallback
    0.46
    การณ์
    0.45
     they
    0.44
    invokeLater
    0.42
    npy
    0.40
     وسلم
    0.40
    Activations Density 2.285%

    No Known Activations