© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14184
    Prev
    Next
    INDEX
    Explanations

    connectors, prepositions, and auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash

    Action verbs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     embreagem
    -0.40
     xmin
    -0.40
     dår
    -0.38
     myndig
    -0.37
     kunder
    -0.37
     justiça
    -0.37
     praça
    -0.36
     blancs
    -0.36
     députés
    -0.36
     atriz
    -0.36
    POSITIVE LOGITS
     earn
    0.99
     invade
    0.98
     accumulate
    0.98
     prepare
    0.96
     introduce
    0.94
     distribute
    0.94
     analyze
    0.93
     investigate
    0.93
     decorate
    0.93
     celebrate
    0.92
    Activations Density 27.708%

    No Known Activations