© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133484
    Prev
    Next
    INDEX
    Explanations

    common issue or error

    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_6_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
    </h2>
    0.89
     κατά
    0.87
     שלא
    0.87
    ”)
    0.86
     ਅ
    0.85
     rapide
    0.85
     الأ
    0.81
     А
    0.80
     अपने
    0.80
     את
    0.80
    POSITIVE LOGITS
    ला
    1.09
    ک
    1.02
    ong
    1.01
    ام
    0.99
    au
    0.93
    <0xB9>
    0.90
    лу
    0.88
    ление
    0.88
    ä
    0.87
    лі
    0.87
    Activations Density 0.014%

    No Known Activations