© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12715
    Prev
    Next
    INDEX
    Explanations

    sales and commerce

    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
     GST
    0.48
     जीएसटी
    0.46
    GST
    0.44
     ⿰
    0.40
     gst
    0.40
    oida
    0.38
     हस्तक्षेप
    0.38
     গঙ্গ
    0.36
     muß
    0.36
    reno
    0.36
    POSITIVE LOGITS
     Er
    0.44
     Maxine
    0.40
     Herbal
    0.39
    莳
    0.38
    ریل
    0.38
     Spring
    0.38
     service
    0.37
     Plan
    0.37
    ताव
    0.37
     Vn
    0.37
    Activations Density 0.011%

    No Known Activations