© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217976
    Prev
    Next
    INDEX
    Explanations

    what impact or relationship

    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
    बारा
    0.40
    尭
    0.36
    稈
    0.36
    ুয়ারি
    0.36
    orra
    0.35
    遗憾
    0.35
    構造
    0.35
    Warum
    0.35
     subgroups
    0.35
    வேறு
    0.34
    POSITIVE LOGITS
    Gaussian
    0.38
     ಗುಣ
    0.37
    otions
    0.36
     خدمة
    0.35
     годах
    0.35
     mur
    0.34
     Roasted
    0.34
    巅
    0.34
    дка
    0.34
     hammered
    0.34
    Activations Density 0.002%

    No Known Activations