© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3862
    Prev
    Next
    INDEX
    Explanations

    information about hockey games, and specifically the score

    oai_token-act-pair · gemini-2.0-flash

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    Filmografie
    -0.60
     DialogInterface
    -0.60
    ServletException
    -0.59
    וך
    -0.55
    createCanvas
    -0.54
    Schritt
    -0.52
     Schritt
    -0.52
     rounds
    -0.51
     terecht
    -0.51
    Auswahl
    -0.51
    POSITIVE LOGITS
    出版年
    0.76
     pinulongan
    0.66
     AssemblyTitle
    0.59
     Normdatei
    0.55
    SpringBootTest
    0.54
    ContentAsync
    0.54
    #
    0.51
    
    0.51
     تضيفلها
    0.50
    onomía
    0.49
    Activations Density 1.138%

    No Known Activations