© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5741
    Prev
    Next
    INDEX
    Explanations

    sentences discussing weather conditions or hiking trips in Los Angeles

    oai_token-act-pair · gemini-2.0-flash

    weather descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     weather
    -1.95
     rainy
    -1.75
     rain
    -1.73
    Weather
    -1.66
     Weather
    -1.64
    weather
    -1.61
     rains
    -1.59
     cold
    -1.57
     colder
    -1.56
     WEATHER
    -1.48
    POSITIVE LOGITS
    addPreferredGap
    0.54
    ComponentModel
    0.50
    istoitu
    0.50
    JAMIN
    0.48
    UserScript
    0.47
    intellij
    0.46
    #+#
    0.46
    jsonwebtoken
    0.45
    graphql
    0.45
    ద్య
    0.45
    Activations Density 0.241%

    No Known Activations