© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14054
    Prev
    Next
    INDEX
    Explanations

    uses of the word "is" near other words considered important.

    oai_token-act-pair · gemini-2.0-flash

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Rather
    -0.81
    rather
    -0.80
     rather
    -0.79
    setVerticalGroup
    -0.75
     quite
    -0.74
    Rather
    -0.73
    quite
    -0.71
    WithIOException
    -0.70
    parsedMessage
    -0.69
     Quite
    -0.69
    POSITIVE LOGITS
    unregister
    0.59
    URR
    0.54
    vax
    0.51
    feof
    0.51
    tagHelperRunner
    0.50
    mondo
    0.50
     obedience
    0.49
     Registered
    0.48
    पया
    0.48
    perk
    0.48
    Activations Density 11.343%

    No Known Activations