© 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. 12524
    Prev
    Next
    INDEX
    Explanations

    instances of the word "of" followed by an article or adjective

    oai_token-act-pair · gemini-2.0-flash

    concepts related to opportunities and support

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

    of

    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
     juridiques
    -0.62
     antemano
    -0.53
     supérieures
    -0.53
     espirituales
    -0.53
     financières
    -0.52
     convaincre
    -0.52
     particulière
    -0.52
    seamnă
    -0.51
     vectorielles
    -0.50
     bestemt
    -0.49
    POSITIVE LOGITS
     exposure
    0.68
     danger
    0.67
     diversity
    0.63
     admission
    0.62
     soil
    0.62
     inspiration
    0.62
     assistance
    0.61
     freedom
    0.61
     visibility
    0.61
     action
    0.60
    Activations Density 10.033%

    No Known Activations