© 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
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 165122
    Prev
    Next
    INDEX
    Explanations

    reflexive

    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_13_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
    وي
    0.55
     utilisés
    0.54
    code
    0.53
    Nombre
    0.53
    v
    0.53
    Res
    0.53
     utilisées
    0.52
    Code
    0.52
    vie
    0.52
    のように
    0.51
    POSITIVE LOGITS
     Nei
    0.57
     Mank
    0.53
     halde
    0.52
     Pawar
    0.52
     Patagonia
    0.52
     Piaget
    0.50
     	i
    0.49
     Murakami
    0.49
     Carnegie
    0.48
     Nepali
    0.48
    Activations Density 0.000%

    No Known Activations