© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8670
    Prev
    Next
    INDEX
    Explanations

    somewhat rare and short parts of words, sometimes medical or legal terms

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    addCriterion
    -1.08
    principalTable
    -1.00
     MainAxisSize
    -0.99
     ModelExpression
    -0.97
    ResumeLayout
    -0.96
    SequentialGroup
    -0.96
    ValueStyle
    -0.94
    rungsseite
    -0.90
    AddHtmlAttribute
    -0.89
    AddTagHelper
    -0.88
    POSITIVE LOGITS
     married
    0.40
     Crosby
    0.39
    inaire
    0.38
     Airlines
    0.38
     تعدى
    0.38
     off
    0.37
    ttino
    0.37
     nghĩa
    0.36
     deuter
    0.36
    dim
    0.36
    Activations Density 0.911%

    No Known Activations