© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245426
    Prev
    Next
    INDEX
    Explanations

    building blocks and resources

    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_40_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
     Classroom
    0.38
    ज्ञा
    0.38
     Science
    0.37
     玄
    0.37
     কেন্দ
    0.37
     Advoc
    0.37
    েন্দ্র
    0.36
     Scientist
    0.36
     এস
    0.36
     العلم
    0.36
    POSITIVE LOGITS
    EPC
    0.43
     comida
    0.42
     sandwich
    0.41
     viande
    0.40
     пище
    0.40
     costruzione
    0.40
     соору
    0.38
     ಹಾಸ
    0.38
    ৱ
    0.38
     nests
    0.38
    Activations Density 0.004%

    No Known Activations