© 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. 11607
    Prev
    Next
    INDEX
    Explanations

    location names associated with the words "in", "to", "from", and "near."

    oai_token-act-pair · gemini-2.0-flash

    words or phrases related to programming

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

    Locations

    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
    UObject
    -0.55
    QtCore
    -0.52
    աց
    -0.51
    kloped
    -0.51
    RetentionPolicy
    -0.51
    ьаж
    -0.51
    Ằ
    -0.50
    adaptiveStyles
    -0.50
     Duct
    -0.50
    WebVitals
    -0.50
    POSITIVE LOGITS
     estekak
    0.67
    UseVisualStyle
    0.62
     consultato
    0.58
     nahilalakip
    0.55
    indest
    0.52
     programu
    0.51
     getItemId
    0.47
    gemaakt
    0.47
     Programs
    0.46
    modb
    0.46
    Activations Density 1.098%

    No Known Activations