© 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. 3630
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with religion, positive emotions, crafting, and marine animals

    oai_token-act-pair · gemini-2.0-flash

    happy

    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
    Joy
    -0.49
    بوابة
    -0.49
     Happiness
    -0.46
     happiness
    -0.44
     happy
    -0.44
    happiness
    -0.43
     felizes
    -0.43
     Joy
    -0.42
    Happiness
    -0.42
    Happy
    -0.42
    POSITIVE LOGITS
    :✨
    0.87
     autorytatywna
    0.81
     فريبيس
    0.81
    fjspx
    0.74
     الحره
    0.69
    ="@+
    0.69
    最快更新
    0.66
    avigation
    0.66
     BorderRadius
    0.64
    RTLR
    0.64
    Activations Density 24.397%

    No Known Activations