© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 64545
    Prev
    Next
    INDEX
    Explanations

    communication and relationships

    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_41_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
     XP
    0.40
     منشور
    0.39
     환
    0.38
     XIA
    0.38
    密
    0.38
    pia
    0.38
    ക്കുള്ള
    0.37
     লো
    0.37
    箜
    0.37
     เนาะ
    0.35
    POSITIVE LOGITS
     breakdown
    1.02
     breakdowns
    0.92
     Breakdown
    0.89
    break
    0.57
    Break
    0.57
     Breakthrough
    0.54
     breakup
    0.53
     Break
    0.52
     breakouts
    0.51
     break
    0.51
    Activations Density 0.008%

    No Known Activations