© 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. 14115
    Prev
    Next
    INDEX
    Explanations

    sentences describing products, scents, or experiences in a positive, sensual and evocative way

    oai_token-act-pair · 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
     smell
    -1.90
     smelled
    -1.85
     smelling
    -1.82
     smells
    -1.77
     scent
    -1.74
    smell
    -1.60
     scents
    -1.60
     odor
    -1.59
     Smell
    -1.54
     aroma
    -1.53
    POSITIVE LOGITS
    EndInit
    0.76
    ge
    0.58
     Moraes
    0.57
    medriver
    0.54
    uxxxx
    0.50
     Seidel
    0.49
    readystatechange
    0.49
    Personensuche
    0.48
     HasFactory
    0.47
     Zell
    0.47
    Activations Density 1.066%

    No Known Activations