© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7012
    Prev
    Next
    INDEX
    Explanations

    a mix of non-English words, month names both abbreviated and full, words related to aristocracy, military, body parts, and vowel-heavy suffixes.

    oai_token-act-pair · gemini-2.0-flash

    Royalty and foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    SpringBootTest
    -0.55
    ds
    -0.51
     Queen
    -0.51
    ains
    -0.50
    endpush
    -0.49
    InjectAttribute
    -0.48
    aska
    -0.48
     captain
    -0.48
    matisch
    -0.48
    씩
    -0.48
    POSITIVE LOGITS
     neceff
    0.75
    béco
    0.73
     становника
    0.69
     насељу
    0.66
    ModelAdmin
    0.66
     himſelf
    0.64
     صوتيه
    0.64
     Swaziland
    0.64
    EDEFAULT
    0.62
    felves
    0.62
    Activations Density 7.567%

    No Known Activations