© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30219
    Prev
    Next
    INDEX
    Explanations

    German language context

    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_40_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
    Shore
    0.42
     spoke
    0.40
     spoken
    0.39
    orderDetails
    0.38
    Detailed
    0.38
     Shore
    0.37
    spoken
    0.37
    乚
    0.37
    itudini
    0.36
    usc
    0.36
    POSITIVE LOGITS
     Latinos
    0.41
     Latin
    0.40
    સ્તુ
    0.39
     amb
    0.39
    oplayer
    0.39
     ইংরাজ
    0.38
     விட
    0.38
     అ
    0.38
     भारत
    0.38
    dans
    0.38
    Activations Density 0.002%

    No Known Activations