© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 66102
    Prev
    Next
    INDEX
    Explanations

    are

    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
     Inheritance
    0.45
    —”
    0.38
     Infinite
    0.38
     HIP
    0.37
    ță
    0.36
    тоо
    0.36
    ุ่ง
    0.36
    }|
    0.35
    |=
    0.35
     deine
    0.35
    POSITIVE LOGITS
     საშუალ
    0.44
    作業
    0.41
    ريكي
    0.41
    λαδή
    0.39
    スタンド
    0.38
    বসাই
    0.37
    かし
    0.37
    PRESSED
    0.37
    spatial
    0.36
    امی
    0.36
    Activations Density 0.002%

    No Known Activations