© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 218652
    Prev
    Next
    INDEX
    Explanations

    medical segmentation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_47_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
     ультра
    0.40
    ATCH
    0.39
     Citizenship
    0.38
    풀
    0.38
     वर्कर्स
    0.38
     pairings
    0.37
     LUT
    0.36
    ৃত্য
    0.36
     transmitting
    0.36
     লি
    0.36
    POSITIVE LOGITS
    ="<?=
    0.38
     treason
    0.37
     Teresa
    0.37
    scrollHeight
    0.35
     Fas
    0.35
     Fasc
    0.35
    FONT
    0.35
     Segmentation
    0.34
     advocating
    0.34
    winds
    0.34
    Activations Density 0.000%

    No Known Activations