© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3709
    Prev
    Next
    INDEX
    Explanations

    chemistry-related terms, especially those relating to nitrates, ammonia and metal compounds

    oai_token-act-pair · gemini-2.0-flash

    nitrate

    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
    moveToFirst
    -0.54
     devriez
    -0.51
     attention
    -0.47
    ึ้น
    -0.47
     renewed
    -0.45
     space
    -0.44
    nbt
    -0.44
    getDouble
    -0.43
    सू
    -0.43
    ametro
    -0.42
    POSITIVE LOGITS
     ProtoMessage
    0.72
    ThroughAttribute
    0.66
    MethodManager
    0.63
     unknownFields
    0.60
     виправивши
    0.60
     ſeveral
    0.59
     faſt
    0.58
     hendes
    0.58
     perſon
    0.57
     StatefulWidget
    0.56
    Activations Density 1.879%

    No Known Activations