© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11530
    Prev
    Next
    INDEX
    Explanations

    words relating to properties being clean, simple, and well-maintained

    oai_token-act-pair · gemini-2.0-flash

    clean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     cleanest
    -1.41
     cleaner
    -1.36
     clean
    -1.31
     Clean
    -1.30
    Clean
    -1.28
    clean
    -1.26
    cleaner
    -1.25
     CLEAN
    -1.20
    CLEAN
    -1.17
     Cleaner
    -1.16
    POSITIVE LOGITS
    aphone
    0.44
    fromCharCode
    0.44
    entran
    0.42
    ьере
    0.42
     跳转至
    0.40
    autoIncrement
    0.39
    Spoljašnje
    0.39
    λιά
    0.38
     reprises
    0.37
    LogFactory
    0.37
    Activations Density 9.352%

    No Known Activations