© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 117101
    Prev
    Next
    INDEX
    Explanations

    information retrieval and overload

    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_38_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
    object
    0.41
    អ
    0.40
    數據
    0.39
     ಅಭ
    0.38
     informasi
    0.37
     informasjon
    0.37
    言葉
    0.37
     informacje
    0.37
    sponsored
    0.37
     information
    0.36
    POSITIVE LOGITS
     প্রবাহ
    0.37
     flow
    0.37
    ünkü
    0.37
     flows
    0.36
     bhavanti
    0.36
    フロー
    0.36
    传
    0.36
     स्ने
    0.35
    😗
    0.35
    üren
    0.35
    Activations Density 0.006%

    No Known Activations