© 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-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 137682
    Prev
    Next
    INDEX
    Explanations

    Formula 1 drivers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    Boost
    0.43
    Boosting
    0.41
    穂
    0.41
     ar
    0.41
    boost
    0.41
     arth
    0.40
     مه
    0.39
    М
    0.38
     Boosting
    0.38
    ряз
    0.38
    POSITIVE LOGITS
     O
    0.57
    aik
    0.47
     ओ
    0.45
    っぱり
    0.40
    価
    0.39
     SOL
    0.38
     Yvonne
    0.38
    O
    0.38
     Os
    0.38
     Aidan
    0.38
    Activations Density 0.001%

    No Known Activations