© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16229
    Prev
    Next
    INDEX
    Explanations

    instances of the word "way" and related words such as "meaningful", "ensure", and "inform"

    oai_token-act-pair · gemini-2.0-flash

    way

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     ways
    -1.71
     way
    -1.66
     Way
    -1.55
    Ways
    -1.54
     Ways
    -1.53
    Way
    -1.45
     WAY
    -1.36
    ways
    -1.32
     WAYS
    -1.30
    way
    -1.29
    POSITIVE LOGITS
    MessageTagHelper
    0.74
     createContext
    0.73
     surla
    0.69
    DataAnnotations
    0.67
    numerusform
    0.66
    MLLoader
    0.66
    usermodel
    0.65
    AddTagHelper
    0.64
    UnusedPrivate
    0.64
    jsonwebtoken
    0.61
    Activations Density 8.890%

    No Known Activations