© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56859
    Prev
    Next
    INDEX
    Explanations

    Si clauses and english ifs

    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
    D
    0.81
    N
    0.71
    د
    0.66
    ut
    0.65
    പി
    0.64
    Про
    0.63
    os
    0.63
    т
    0.63
    ar
    0.62
    list
    0.62
    POSITIVE LOGITS
     UCC
    0.61
     Massive
    0.60
     UHS
    0.60
     Coral
    0.57
     U
    0.56
     વર્ષ
    0.55
     massive
    0.54
    ियंस
    0.54
     UAS
    0.54
     EMS
    0.53
    Activations Density 0.003%

    No Known Activations