© 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. 9186
    Prev
    Next
    INDEX
    Explanations

    the capital 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
     Paglinawan
    -1.07
     Roskov
    -1.01
     AssemblyCulture
    -0.93
     kasarigan
    -0.90
    CppMethod
    -0.90
    SequentialGroup
    -0.89
     AssemblyCompany
    -0.88
     informée
    -0.88
    awtextra
    -0.88
     INTERESAR
    -0.88
    POSITIVE LOGITS
     la
    0.55
     Can
    0.54
     L
    0.51
    g
    0.51
     (
    0.51
     l
    0.50
    th
    0.50
     th
    0.49
    er
    0.49
     F
    0.49
    Activations Density 0.462%

    No Known Activations