© 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. 1527
    Prev
    Next
    INDEX
    Explanations

    loving kindness

    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
     ഒ
    0.37
    ्वा
    0.37
    yaratan
    0.36
    氧
    0.36
    やすい
    0.36
     Kerm
    0.34
    Explain
    0.34
    uxxxx
    0.34
    ாளர்
    0.33
     keny
    0.33
    POSITIVE LOGITS
    -
    0.56
    ‑
    0.48
     Kindness
    0.48
     kindness
    0.47
     kindly
    0.45
    ‐
    0.44
     greetings
    0.43
    -...
    0.42
     arrives
    0.41
    ־
    0.41
    Activations Density 0.098%

    No Known Activations