© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10023
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash

    would

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     mourut
    -0.66
     laissant
    -0.66
     teniendo
    -0.65
     llegando
    -0.64
     diciendo
    -0.63
     grecque
    -0.63
     pidiendo
    -0.61
     llevando
    -0.61
     venait
    -0.61
     habiendo
    -0.60
    POSITIVE LOGITS
     have
    1.29
     apply
    1.21
     continue
    1.16
     serve
    1.10
     receive
    1.10
     undergo
    1.09
     look
    1.08
     respond
    1.08
     keep
    1.07
     introduce
    1.07
    Activations Density 9.081%

    No Known Activations