© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6024
    Prev
    Next
    INDEX
    Explanations

    the word "whose."

    oai_token-act-pair · gemini-2.0-flash

    whose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     betweenstory
    -1.25
    OGND
    -1.17
    Personensuche
    -1.08
    ьаж
    -0.97
    WithIOException
    -0.96
     fevere
    -0.96
     saveiro
    -0.95
     purpoſe
    -0.95
    AccessorTable
    -0.93
     mohair
    -0.93
    POSITIVE LOGITS
     “
    0.88
     
    0.84
    ’
    0.73
     "
    0.71
     main
    0.69
     ‘
    0.68
     is
    0.63
    '
    0.63
    “
    0.62
     major
    0.58
    Activations Density 2.835%

    No Known Activations