© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11798
    Prev
    Next
    INDEX
    Explanations

    the word "sense" with nearby words such as "of", "humor", or adjectives such as "great"

    oai_token-act-pair · gemini-2.0-flash

    sense

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ArrowToggle
    -0.64
     Etrus
    -0.63
     xenia
    -0.63
     Cæsar
    -0.61
     createSlice
    -0.60
     Krakowie
    -0.60
     peasants
    -0.59
     vanadium
    -0.59
     Efq
    -0.58
     resourceCulture
    -0.57
    POSITIVE LOGITS
    脚注の使い方
    0.64
    ParallelGroup
    0.50
    Personensuche
    0.47
    PORARY
    0.44
    IGraphics
    0.43
     descarga
    0.43
    angliski
    0.43
    🧹
    0.42
     meubles
    0.41
    hibitor
    0.41
    Activations Density 2.143%

    No Known Activations