© 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. 9639
    Prev
    Next
    INDEX
    Explanations

    the word "a" and words that commonly come before or after it

    oai_token-act-pair · gemini-2.0-flash

    a

    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
    Couple
    -0.58
    UnitTesting
    -0.57
    theless
    -0.57
    ãi
    -0.56
     couple
    -0.55
     několik
    -0.51
    UnknownFieldSet
    -0.51
    Lots
    -0.51
     pár
    -0.50
     Couple
    -0.49
    POSITIVE LOGITS
     number
    3.33
    number
    3.06
    Number
    2.83
     Number
    2.73
     NUMBER
    2.55
     número
    2.42
    NUMBER
    2.38
     numbers
    2.27
     numero
    2.03
     nummer
    1.91
    Activations Density 2.432%

    No Known Activations