© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 64723
    Prev
    Next
    INDEX
    Explanations

    reactive attachment disorder

    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
     Distress
    0.72
     distress
    0.70
     distressed
    0.56
     impairment
    0.52
    素
    0.45
    regul
    0.42
     Imp
    0.41
     impair
    0.41
     regulation
    0.41
     Sab
    0.41
    POSITIVE LOGITS
    ربه
    0.44
     draper
    0.39
    nse
    0.38
    piele
    0.37
    ニメ
    0.37
     Siegel
    0.37
    intégration
    0.36
    柤
    0.36
    arına
    0.36
     seams
    0.35
    Activations Density 0.003%

    No Known Activations