© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13919
    Prev
    Next
    INDEX
    Explanations

    the word "advanced," and also other words that might be related to advancements in technology or science

    oai_token-act-pair · gemini-2.0-flash

    advanced

    np_max-act · gemini-2.0-flash

    advanced

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    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
    Negative Logits
     us
    -0.69
     its
    -0.65
     itself
    -0.63
     fenô
    -0.63
     menem
    -0.59
    Хьажоргаш
    -0.59
    __':
    -0.58
    ArgsConstructor
    -0.58
    MLLoader
    -0.58
     it
    -0.57
    POSITIVE LOGITS
     Monfieur
    1.07
     Houſe
    1.02
    ſelf
    0.94
     Reſ
    0.94
     houſe
    0.91
     myſelf
    0.89
     Diſ
    0.89
     Majefty
    0.88
    .")
    0.85
     Conſ
    0.85
    Activations Density 1.424%

    No Known Activations