© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7845
    Prev
    Next
    INDEX
    Explanations

    the word "by" or phrases indicating authorship

    oai_token-act-pair · gemini-2.0-flash

    by, of

    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
    Negative Logits
    PPS
    -0.52
     Rayon
    -0.51
     Heft
    -0.50
    idine
    -0.49
    sibility
    -0.48
     Stu
    -0.47
     PPS
    -0.47
     관
    -0.46
    素
    -0.46
     Bew
    -0.45
    POSITIVE LOGITS
    __":
    0.86
    __':
    0.80
     يتيمه
    0.79
    +#+#
    0.78
     GenerationType
    0.73
    PreferredItem
    0.68
     spesa
    0.65
    الدراسه
    0.65
    SpringBootTest
    0.63
    OGND
    0.63
    Activations Density 0.869%

    No Known Activations