© 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. 13189
    Prev
    Next
    INDEX
    Explanations

    uses of the word "moral" and related concepts such as religion, beliefs, and social behavior.

    oai_token-act-pair · gemini-2.0-flash

    moral

    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
     moral
    -2.19
     Moral
    -1.99
    moral
    -1.99
     MOR
    -1.98
     ethical
    -1.98
    Mor
    -1.95
     morally
    -1.94
     Mor
    -1.91
    MOR
    -1.91
    Moral
    -1.87
    POSITIVE LOGITS
    transQ
    0.52
    SpringBootTest
    0.52
     Sylvie
    0.45
    complexType
    0.44
     Selecciona
    0.43
     Cummings
    0.42
    createNewFile
    0.42
    computa
    0.42
    گا
    0.42
     الرياضيه
    0.42
    Activations Density 3.104%

    No Known Activations