© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10173
    Prev
    Next
    INDEX
    Explanations

    the word "significantly"

    oai_token-act-pair · gemini-2.0-flash

    significantly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Lightboxes
    -1.01
    yntaxException
    -0.91
     Seeder
    -0.90
    IsContent
    -0.89
    Personendaten
    -0.88
    featureID
    -0.86
     Walkover
    -0.86
    fillType
    -0.85
     StringTokenizer
    -0.83
    AndEndTag
    -0.83
    POSITIVE LOGITS
     variés
    0.65
     indústria
    0.65
     férfi
    0.63
     száll
    0.62
     variedade
    0.61
     riuscito
    0.60
     ordinaires
    0.60
     comerciais
    0.60
     stedet
    0.59
     peuples
    0.59
    Activations Density 2.823%

    No Known Activations