© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13134
    Prev
    Next
    INDEX
    Explanations

    a variety of markup syntax, mathematical formulas, or code snippets, perhaps identifying different sections or elements within a document.

    oai_token-act-pair · gemini-2.0-flash

    6

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    WriteBarrier
    -0.86
     typelib
    -0.82
    EndContext
    -0.79
     محفوظة
    -0.77
     صوتيه
    -0.72
     الرياضيه
    -0.72
     लेकर
    -0.67
     مرئيه
    -0.66
    GEBURTS
    -0.64
    ItemBackground
    -0.64
    POSITIVE LOGITS
    ParallelGroup
    0.50
    photobucket
    0.42
    zahn
    0.42
    unda
    0.42
     opr
    0.40
     Mathematik
    0.40
     play
    0.40
    grama
    0.39
    caught
    0.38
     reed
    0.38
    Activations Density 1.837%

    No Known Activations