© 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. 8534
    Prev
    Next
    INDEX
    Explanations

    words related to mathematics, and "play on words" and "tomatoes"

    oai_token-act-pair · gemini-2.0-flash

    repeated words and symbols

    np_max-act · 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
     فريبيس
    -0.69
    UVWXYZ
    -0.68
    onViewCreated
    -0.68
    כשיו
    -0.66
     ujednoznacz
    -0.65
    CloseOperation
    -0.63
     userSchema
    -0.60
    ungeon
    -0.59
     OnEnable
    -0.59
    kegaard
    -0.58
    POSITIVE LOGITS
    istoitu
    0.50
    wyneth
    0.48
    Substitute
    0.47
     plexus
    0.46
     Nexus
    0.46
     précieux
    0.45
    킴
    0.45
    PageContext
    0.44
     pince
    0.44
    etwork
    0.44
    Activations Density 0.853%

    No Known Activations