© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 3840
    Prev
    Next
    INDEX
    Explanations

    the word "gray" (and its variants, such as "grey" and "graying").

    oai_token-act-pair · gemini-2.0-flash

    gray/grey

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Difficult
    -0.82
     difficult
    -0.77
    saraba
    -0.76
    Difficult
    -0.76
    difficult
    -0.75
    UnusedPrivate
    -0.74
    oa̍t
    -0.74
    Portale
    -0.73
    tvguidetime
    -0.73
     difficiles
    -0.72
    POSITIVE LOGITS
     nî
    0.45
     "..\..\
    0.42
    ames
    0.41
    ASM
    0.41
     bas
    0.40
    ADC
    0.38
     yol
    0.38
    eraus
    0.37
    ukų
    0.37
     media
    0.37
    Activations Density 0.490%

    No Known Activations