© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3379
    Prev
    Next
    INDEX
    Explanations

    phrases questioning morality or what is wrong with something

    oai_token-act-pair · gemini-2.0-flash

    wrong

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    QUADS
    -0.57
     Exclusion
    -0.52
    MUM
    -0.50
     giuri
    -0.46
     recevez
    -0.45
     ricor
    -0.45
    énario
    -0.45
     ([]
    -0.45
    ozof
    -0.44
     Inclusion
    -0.44
    POSITIVE LOGITS
     initComponents
    0.83
     للمعارف
    0.78
    Hochspringen
    0.69
    ValueStyle
    0.66
    GIVEREF
    0.65
     LoggerFactory
    0.64
    ValueGenerated
    0.64
    Portale
    0.63
     propOrder
    0.62
     насељу
    0.61
    Activations Density 0.786%

    No Known Activations