© 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. 3403
    Prev
    Next
    INDEX
    Explanations

    mentions of weather events, locations, and dates, especially in the context of legal or official proceedings

    oai_token-act-pair · gemini-2.0-flash

    hurricanes and storms

    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
     ujednoznacz
    -0.79
     estekak
    -0.75
    CppMethod
    -0.66
    rrggbb
    -0.66
    PhysRevD
    -0.62
    OGND
    -0.61
    Sucesor
    -0.60
    localctx
    -0.59
    InjectAttribute
    -0.58
     חיצוניים
    -0.58
    POSITIVE LOGITS
     vatt
    0.60
     Crespo
    0.58
     overheat
    0.54
    nergie
    0.53
     Honeymoon
    0.52
     snabb
    0.50
     vibrational
    0.50
    SBATCH
    0.49
     suspendu
    0.49
     cilind
    0.49
    Activations Density 4.940%

    No Known Activations