© 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
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208679
    Prev
    Next
    INDEX
    Explanations

    superficial social interactions

    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_20_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
    いの
    0.52
     چاہے
    0.49
     ንጥረ
    0.48
    оте
    0.45
    Solo
    0.45
    े
    0.45
    ᑭ
    0.44
     समझाने
    0.44
    ヒト
    0.43
    🫂
    0.43
    POSITIVE LOGITS
     velocity
    0.49
     Accelerated
    0.47
     issued
    0.47
     legit
    0.47
     Yellow
    0.46
     Vinyl
    0.46
     एडिट
    0.46
    荕
    0.46
     t
    0.45
     Fatigue
    0.45
    Activations Density 0.001%

    No Known Activations