© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38645
    Prev
    Next
    INDEX
    Explanations

    course codes and abbreviations

    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_11_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
    მოს
    0.54
    žití
    0.54
    ]。
    0.52
    ））
    0.52
    кій
    0.52
    ्लो
    0.51
    ControlButton
    0.51
    жы
    0.50
    锜
    0.50
    жный
    0.49
    POSITIVE LOGITS
    t
    0.61
    í
    0.58
    и
    0.54
    ly
    0.52
     espan
    0.50
     những
    0.49
     Smithsonian
    0.49
    ya
    0.48
     dai
    0.48
     alcune
    0.48
    Activations Density 0.009%

    No Known Activations