© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198786
    Prev
    Next
    INDEX
    Explanations

    rice

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    Locale
    0.48
    喹
    0.41
     Lain
    0.39
    ANNEL
    0.39
     vipp
    0.39
    DebuggingMode
    0.39
    댑
    0.38
     spol
    0.38
    뎁
    0.38
    Pain
    0.37
    POSITIVE LOGITS
     field
    0.53
     поле
    0.44
    field
    0.44
     Field
    0.41
     mag
    0.39
     campo
    0.39
     HTMLSc
    0.38
    ènes
    0.38
    曆
    0.37
    tag
    0.37
    Activations Density 0.000%

    No Known Activations