© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8538
    Prev
    Next
    INDEX
    Explanations

    words which are in the context of describing people and personalities

    oai_token-act-pair · gemini-2.0-flash

    unusual or specific terms and phrases

    np_token-act-pair-logits · gpt-4o-mini

    attractive people

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    存于互联网档案馆
    -0.58
    Билгалдахарш
    -0.57
    RegressionTest
    -0.54
     تانيه
    -0.52
    findpost
    -0.52
     Greedy
    -0.51
    Skocz
    -0.51
     estimés
    -0.51
     mares
    -0.51
    Datuak
    -0.51
    POSITIVE LOGITS
     Waray
    0.69
    chyma
    0.61
     fresh
    0.61
    PANY
    0.56
    fresh
    0.53
    0.53
    aroa
    0.52
     down
    0.52
    iecie
    0.52
    bably
    0.52
    Activations Density 2.067%

    No Known Activations