© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15414
    Prev
    Next
    INDEX
    Explanations

    connecting words and prepositions near references to a specific group of people or location

    oai_token-act-pair · gemini-2.0-flash

    HBCUs and African-American history

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     AttributeSet
    -0.54
    EndGlobalSection
    -0.52
     للمعارف
    -0.52
     paramString
    -0.51
    Diweddarwch
    -0.50
     Prest
    -0.49
     Adama
    -0.49
     biệt
    -0.48
    álním
    -0.48
     vuitton
    -0.47
    POSITIVE LOGITS
     historically
    0.65
     Historically
    0.62
     Howard
    0.55
    WarningLevel
    0.53
     H
    0.52
     veto
    0.51
    histor
    0.50
     Fisk
    0.50
     rospy
    0.50
    AnchorTagHelper
    0.50
    Activations Density 1.440%

    No Known Activations