© 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. 9793
    Prev
    Next
    INDEX
    Explanations

    the letters "M" and "O" in isolation, potentially indicating the presence of acronyms or initials

    oai_token-act-pair · gemini-2.0-flash

    Detects snippets of information

    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
     nakalista
    -0.75
    iocene
    -0.57
     calendriers
    -0.54
     MenuView
    -0.54
    σμο
    -0.51
    ainville
    -0.51
    UnknownFields
    -0.50
     fieldNum
    -0.50
    FormTagHelper
    -0.49
    ERR
    -0.47
    POSITIVE LOGITS
     урна
    0.61
     ویکی‌پدیا
    0.60
     geslacht
    0.53
    PRWEB
    0.51
    Демографія
    0.50
    govine
    0.50
     CommandType
    0.49
     StringTokenizer
    0.49
    gonic
    0.48
     ISNI
    0.47
    Activations Density 1.821%

    No Known Activations