© 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. 15868
    Prev
    Next
    INDEX
    Explanations

    the letter "M"

    oai_token-act-pair · gemini-2.0-flash

    M

    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
    AsUp
    -0.88
     חיצוניים
    -0.85
     AssemblyProduct
    -0.82
    ContentAsync
    -0.82
    IndentedString
    -0.81
     Wikimédia
    -0.77
     ostavi
    -0.73
     initComponents
    -0.70
    DeleteBehavior
    -0.69
    MemoryWarning
    -0.68
    POSITIVE LOGITS
    ando
    0.41
    UC
    0.37
    avis
    0.37
    ylar
    0.34
    ANDO
    0.34
    UCK
    0.34
    amb
    0.33
    ånga
    0.33
    GA
    0.32
    uille
    0.32
    Activations Density 1.649%

    No Known Activations