© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212917
    Prev
    Next
    INDEX
    Explanations

    Gran Bretaña / UK

    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_5_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
     as
    1.10
    RA
    0.88
     to
    0.81
     It
    0.80
    </h3>
    0.79
    map
    0.77
    ↵↵
    0.77
     Have
    0.75
     aswell
    0.73
     FirebaseAuth
    0.72
    POSITIVE LOGITS
    i
    1.22
    ي
    1.21
    <0x80>
    1.09
    се
    0.96
    é
    0.92
    ни
    0.91
    ای
    0.91
    も
    0.90
    ار
    0.89
    ா
    0.87
    Activations Density 0.000%

    No Known Activations