© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4540
    Prev
    Next
    INDEX
    Explanations

    the word "section" and related terms in technical documents

    oai_token-act-pair · gemini-2.0-flash

    section

    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
     Amadeus
    -0.75
     Terrestrial
    -0.74
     Strict
    -0.73
     Supervision
    -0.71
     moment
    -0.70
    rops
    -0.69
     Largo
    -0.68
    ÉM
    -0.68
     Moment
    -0.67
     Rooster
    -0.67
    POSITIVE LOGITS
     Мексичка
    0.90
     '\\;'
    0.86
    انيف
    0.85
    ]")]
    0.82
    Diweddarwch
    0.80
    ])));
    0.79
    ."));
    0.76
    SharedDtor
    0.75
     мәкал
    0.74
    AndEndTag
    0.71
    Activations Density 1.154%

    No Known Activations