© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 195852
    Prev
    Next
    INDEX
    Explanations

    coordinates followed by comma

    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_26_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
    volv
    0.43
     Miocene
    0.41
     बौद्ध
    0.40
     मुगल
    0.40
    redientes
    0.39
     ज़रूर
    0.39
     ब्रिटिश
    0.38
    淌
    0.38
    ҷ
    0.37
    готов
    0.37
    POSITIVE LOGITS
     seam
    0.40
    N
    0.40
    Intu
    0.40
    排
    0.40
     altas
    0.39
    DAQ
    0.38
    intuitive
    0.38
     επα
    0.38
     tete
    0.37
    NA
    0.37
    Activations Density 0.000%

    No Known Activations