© 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. 33735
    Prev
    Next
    INDEX
    Explanations

    listening and understanding

    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
     Ев
    0.35
     고객
    0.34
    缦
    0.34
    ustomer
    0.34
     müşter
    0.32
    客户
    0.31
     klant
    0.31
     selben
    0.31
    ลูกค้า
    0.30
     khách
    0.30
    POSITIVE LOGITS
    hul
    0.35
    न्वयन
    0.35
     mengingat
    0.34
     sape
    0.33
     مرب
    0.33
     SIA
    0.32
     সহ্য
    0.32
    ಗ
    0.32
    ပြု
    0.32
    洵
    0.32
    Activations Density 0.001%

    No Known Activations