© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10451
    Prev
    Next
    INDEX
    Explanations

    words related to business, government, and formal titles

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Personendaten
    -0.68
    thâu
    -0.50
    rzost
    -0.49
     aDecoder
    -0.49
    webElementXpaths
    -0.48
    PyExc
    -0.47
     esternos
    -0.46
     дописавши
    -0.46
    海道
    -0.46
    opcao
    -0.45
    POSITIVE LOGITS
     Dada
    0.55
     domestiques
    0.55
     متعلقه
    0.55
     APPARATUS
    0.52
     الاطلاع
    0.52
     houſe
    0.52
    исленность
    0.51
    zji
    0.51
    Initialization
    0.50
     กรัม
    0.49
    Activations Density 4.815%

    No Known Activations