© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 101306
    Prev
    Next
    INDEX
    Explanations

    noise reduction or hundred percent

    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_16_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
     internacionales
    0.08
     عن
    0.08
    ٤
    0.08
    ،
    0.08
    에
    0.07
    ala
    0.07
     tentang
    0.07
     детали
    0.07
    ៤
    0.07
     ৬
    0.07
    POSITIVE LOGITS
     gdyż
    0.08
     elevating
    0.07
     ہوگی
    0.07
    凝聚
    0.07
    이션
    0.07
     building
    0.07
     immutable
    0.07
     वास्तु
    0.07
     chá
    0.07
    架构
    0.07
    Activations Density 0.008%

    No Known Activations