© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125616
    Prev
    Next
    INDEX
    Explanations

    number of

    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
    عدد
    0.41
     Fewer
    0.38
    artwork
    0.38
    ቃት
    0.37
     repetitions
    0.37
    欣赏
    0.37
    人數
    0.37
     孔
    0.36
     শুনতে
    0.35
    溌
    0.35
    POSITIVE LOGITS
     সম্ব
    0.41
     goodness
    0.40
     perspectiva
    0.40
     Timeline
    0.40
     parte
    0.40
     interaction
    0.39
    pen
    0.39
     taxation
    0.39
     portions
    0.38
     deal
    0.38
    Activations Density 0.004%

    No Known Activations