© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5392
    Prev
    Next
    INDEX
    Explanations

    words related to event planning and surveying using the internet

    oai_token-act-pair · gemini-2.0-flash

    words related to meetings and conferences

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

    meetings and conferences

    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
    AsUp
    -0.74
    TagHelper
    -0.61
     ujednoznacz
    -0.59
     portefeuille
    -0.59
     CGSize
    -0.58
    JspWriter
    -0.57
     isInitialized
    -0.54
    WritableDatabase
    -0.54
    casian
    -0.53
     بيها
    -0.52
    POSITIVE LOGITS
     meeting
    1.59
     Meeting
    1.52
     conference
    1.47
    Meeting
    1.44
    meeting
    1.39
     MEETING
    1.30
     Conference
    1.28
     meetings
    1.26
    Conference
    1.23
     Meetings
    1.19
    Activations Density 1.134%

    No Known Activations