© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10847
    Prev
    Next
    INDEX
    Explanations

    prepositions and articles

    oai_token-act-pair · gemini-2.0-flash

    International events and organizations

    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
    CGRectMake
    -0.55
    initComponents
    -0.53
     محفوظة
    -0.52
     addSubview
    -0.52
    anthes
    -0.51
    PRNewswire
    -0.51
    CreateModel
    -0.49
     <>",
    -0.49
     EconPapers
    -0.48
    UnusedPrivate
    -0.48
    POSITIVE LOGITS
    kloped
    0.56
     utafitiHapana
    0.56
    StructEnd
    0.56
     ammat
    0.51
     pinulongan
    0.50
    DockStyle
    0.50
     AssemblyProduct
    0.49
     يتيمه
    0.48
    Sklici
    0.48
    ContentAsync
    0.48
    Activations Density 2.743%

    No Known Activations