© 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
    2. Gemma-3-27B-IT
    3. 37-GEMMASCOPE-2-TRANSCODER-262K
    4. 203330
    Prev
    Next
    INDEX
    Explanations

    orange, yellow, creative, optimistic

    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_37_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
    啍
    0.41
    ゲージ
    0.37
     prismatic
    0.37
     फीट
    0.36
     lemon
    0.36
     गिफ्ट
    0.36
     bonnet
    0.36
    パターン
    0.35
     faculties
    0.35
     እር
    0.35
    POSITIVE LOGITS
     aloud
    0.44
    пут
    0.38
     |,
    0.37
    ӧ
    0.36
     Babylon
    0.36
     نی
    0.35
     prosecuted
    0.34
     specifically
    0.34
     prosecution
    0.34
     coral
    0.34
    Activations Density 0.001%

    No Known Activations