© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 142976
    Prev
    Next
    INDEX
    Explanations

    industry sectors

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     تش
    0.41
    transport
    0.40
    ウ
    0.39
    우
    0.38
     paw
    0.36
     মাধ্য
    0.36
     транспорти
    0.36
     пись
    0.36
    tailed
    0.35
    꽝
    0.35
    POSITIVE LOGITS
     प्रोडक्ट्स
    0.38
    순
    0.38
    కా
    0.38
     Selector
    0.38
     Pediatr
    0.37
     selectors
    0.37
    etric
    0.37
    superblock
    0.37
    ຄວາມ
    0.36
    selector
    0.36
    Activations Density 0.001%

    No Known Activations