© 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. 59934
    Prev
    Next
    INDEX
    Explanations

    en enfoques

    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
    ни
    1.35
    를
    1.25
    ى
    1.24
    </h1>
    1.14
     on
    1.13
    <0x0D>
    1.02
    는
    1.02
    </h2>
    1.02
    好吃
    1.01
    я
    1.01
    POSITIVE LOGITS
    ।
    1.05
     focuss
    1.02
     modelli
    0.98
     beneficios
    0.93
     trabajos
    0.91
     locaux
    0.90
     singoli
    0.89
    म्ब
    0.87
    lerinde
    0.86
     реализации
    0.86
    Activations Density 0.006%

    No Known Activations