© 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. 9446
    Prev
    Next
    INDEX
    Explanations

    gibberish and potentially foreign words related to religion and folklore

    oai_token-act-pair · 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
    <bos>
    -0.51
    RectangleBorder
    -0.44
    DoubleQuotes
    -0.41
    AddTagHelper
    -0.38
     AssemblyProduct
    -0.37
     BoxDecoration
    -0.35
    GEBURTSDATUM
    -0.34
    ָד
    -0.34
     Monfieur
    -0.33
    ByVersion
    -0.33
    POSITIVE LOGITS
    )=>{
    0.52
     n
    0.49
     kh
    0.49
    -]
    0.48
    ništ
    0.48
     khe
    0.48
     t
    0.47
    ("]");
    0.47
     r
    0.47
    ]+=
    0.47
    Activations Density 17.559%

    No Known Activations