© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9494
    Prev
    Next
    INDEX
    Explanations

    language related to weather and clothing appropriate for that weather

    oai_token-act-pair · gemini-2.0-flash

    weather

    np_max-act-logits · 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
     weather
    -2.61
     climate
    -2.47
     Weather
    -2.42
    Weather
    -2.39
    weather
    -2.27
     WEATHER
    -2.22
     Climate
    -2.22
    Climate
    -2.17
    WEATHER
    -2.13
    climate
    -2.11
    POSITIVE LOGITS
    cshtml
    0.63
    XmlAccessorType
    0.61
    GraphicsUnit
    0.60
    IBOutlet
    0.59
    BoxLayout
    0.56
     <=",
    0.56
    addPreferredGap
    0.56
    новништво
    0.55
    MLLoader
    0.54
    INCREF
    0.54
    Activations Density 1.286%

    No Known Activations