© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140562
    Prev
    Next
    INDEX
    Explanations

    T cell receptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MILLER
    0.48
    '
    0.46
     calculer
    0.43
     malice
    0.43
     vencedor
    0.43
    кован
    0.42
     balances
    0.42
     battled
    0.42
     avuto
    0.41
     LEG
    0.40
    POSITIVE LOGITS
    Pat
    0.47
    log
    0.44
    light
    0.42
    Signs
    0.42
    t
    0.42
    tttt
    0.41
    っています
    0.40
    tig
    0.39
    ✿
    0.39
    HashMap
    0.38
    Activations Density 0.004%

    No Known Activations