© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111516
    Prev
    Next
    INDEX
    Explanations

    Basque words (sorgin) and Spanish (una, juntos)

    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_2_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
    u
    0.86
    os
    0.82
    *'
    0.82
     infancy
    0.81
    NUCLEAR
    0.81
    는
    0.79
    ER
    0.79
    нее
    0.79
    AUDIO
    0.78
    UTILS
    0.78
    POSITIVE LOGITS
    ки
    1.09
     \
    1.04
    ال
    1.04
    。
    1.02
    است
    1.02
    profit
    1.00
    pct
    1.00
    fte
    0.99
     has
    0.98
    માં
    0.97
    Activations Density 0.001%

    No Known Activations