© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220300
    Prev
    Next
    INDEX
    Explanations

    donating plasma or organs

    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_31_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
     posthum
    0.44
     cadáver
    0.43
    移植
    0.42
     cada
    0.41
    ograft
    0.41
     नैतिक
    0.41
    דם
    0.40
    屍
    0.40
     ethically
    0.40
     ethical
    0.39
    POSITIVE LOGITS
    Chevron
    0.39
     Isolation
    0.37
     remote
    0.37
     මු
    0.37
     স্র
    0.37
    ാവ്
    0.36
     isolation
    0.36
    天然
    0.36
     Population
    0.36
     orders
    0.34
    Activations Density 0.008%

    No Known Activations