© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10276
    Prev
    Next
    INDEX
    Explanations

    words related to skincare, shaving, creams, and related products

    oai_token-act-pair · gemini-2.0-flash

    Fluids and materials

    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
     wines
    -0.82
     Wines
    -0.78
     teas
    -0.76
     coffees
    -0.75
     cheeses
    -0.67
     waters
    -0.62
     silks
    -0.62
     beers
    -0.62
    Foods
    -0.61
     RNAs
    -0.61
    POSITIVE LOGITS
     Administrativna
    0.80
     للاسماء
    0.77
     AssemblyTitle
    0.75
     مرئيه
    0.75
     تانيه
    0.69
    TagMode
    0.67
    DrawerToggle
    0.65
     Савезне
    0.64
     AssemblyCulture
    0.64
    Tikang
    0.64
    Activations Density 6.180%

    No Known Activations