© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11242
    Prev
    Next
    INDEX
    Explanations

    words or phrases about hygiene and odor reduction

    oai_token-act-pair · gemini-2.0-flash

    Smell

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    GEBURTSDATUM
    -0.86
    EndInit
    -0.81
    uxxxx
    -0.70
     Rake
    -0.60
    ngrx
    -0.59
    }$)
    -0.59
    Fns
    -0.58
    PreExecute
    -0.56
    mbolo
    -0.55
     SPI
    -0.55
    POSITIVE LOGITS
     smell
    1.35
     smells
    1.25
     smelling
    1.22
     stink
    1.16
     odor
    1.12
     smelled
    1.12
     scent
    1.10
     st
    1.10
     Smell
    1.09
     fragrance
    1.08
    Activations Density 1.621%

    No Known Activations