© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4506
    Prev
    Next
    INDEX
    Explanations

    mentions of universities

    oai_token-act-pair · gemini-2.0-flash

    references to universities

    np_token-act-pair-logits · gpt-4o-mini

    University

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    PostInfinity
    -0.65
     gyhoeddwyd
    -0.63
     habet
    -0.62
     Hathaway
    -0.59
     nahilalakip
    -0.58
     smtplib
    -0.56
     cherchés
    -0.55
     Eres
    -0.55
    はじめに
    -0.54
     umane
    -0.54
    POSITIVE LOGITS
     AssemblyTitle
    0.69
    सन्दर्भ
    0.57
    코
    0.45
    Collegamenti
    0.44
    Spor
    0.44
    )?.
    0.44
    ///</
    0.44
     intptr
    0.43
    ieta
    0.43
    IVEREF
    0.43
    Activations Density 0.425%

    No Known Activations