© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10976
    Prev
    Next
    INDEX
    Explanations

    code, specifically related to charts, phonebooks, classes, and caching

    oai_token-act-pair · gemini-2.0-flash

    code, data structures

    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
    Билгалдахарш
    -0.44
     di
    -0.43
     ko
    -0.42
     у
    -0.40
     pri
    -0.39
     δ
    -0.39
    P
    -0.39
     i
    -0.39
     poitrine
    -0.38
     J
    -0.38
    POSITIVE LOGITS
    Datuak
    1.03
     AssemblyTitle
    0.92
     myſelf
    0.91
     Efq
    0.89
     propOrder
    0.88
    HtmlAttribute
    0.85
     purpoſe
    0.83
    MemoryWarning
    0.82
    titleMargin
    0.81
     الرياضيه
    0.81
    Activations Density 2.248%

    No Known Activations