© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 148
    Prev
    Next
    INDEX
    Explanations

    medical terms related to colds and respiratory illnesses

    oai_token-act-pair · gemini-2.0-flash

    common cold

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    ydı
    -0.44
    MergeFrom
    -0.44
     Большая
    -0.42
    ifikant
    -0.40
    不懂
    -0.40
    WindowConstants
    -0.39
    AutoScaleMode
    -0.38
    学
    -0.38
    ciclop
    -0.38
    DataContract
    -0.38
    POSITIVE LOGITS
     المعيارى
    0.87
     ujednoznacz
    0.63
     intersected
    0.61
     interconnect
    0.60
    :+:
    0.59
    CROSSTALK
    0.59
    GHIJKLM
    0.58
     intersect
    0.58
     Constitucional
    0.57
     Normdatei
    0.56
    Activations Density 8.917%

    No Known Activations