© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201096
    Prev
    Next
    INDEX
    Explanations

    obsessive-compulsive 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_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
    ั่ว
    0.43
    ';"+
    0.41
     प्रेग्न
    0.40
     पॉलिट
    0.40
     ລັບ
    0.38
    job
    0.37
    𒀜
    0.37
     कस्बे
    0.36
    炰
    0.36
    байд
    0.36
    POSITIVE LOGITS
     OCD
    1.09
     obsessive
    0.95
     compuls
    0.89
     obsess
    0.88
     compulsive
    0.86
     Obs
    0.85
    Obs
    0.79
     obs
    0.79
     obses
    0.73
     obsession
    0.71
    Activations Density 0.003%

    No Known Activations