© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 51300
    Prev
    Next
    INDEX
    Explanations

    object followed by descriptor

    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_31_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
    Wash
    0.34
     USD
    0.32
    žky
    0.32
     പഴയ
    0.32
    Mua
    0.31
    좁
    0.31
     निशुल्क
    0.30
     (!$
    0.29
    раздо
    0.29
    kev
    0.28
    POSITIVE LOGITS
    蚂
    0.36
    administration
    0.33
     administration
    0.30
     Antennes
    0.30
     breathing
    0.29
     tablero
    0.29
     blur
    0.29
     веб
    0.29
     reassure
    0.29
     puberty
    0.29
    Activations Density 0.002%

    No Known Activations