© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 85222
    Prev
    Next
    INDEX
    Explanations

    medical issues, problems, attention, advice, intervention, conditions, risks, emergency

    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_18_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     resistive
    0.44
    抵抗
    0.44
     salicylic
    0.44
     tache
    0.43
     positron
    0.43
     erythemat
    0.42
    😣
    0.42
     distal
    0.41
    鿉
    0.41
     resists
    0.41
    POSITIVE LOGITS
    Wit
    0.44
    Th
    0.41
    GE
    0.41
    Mills
    0.38
     ঘটে
    0.38
    Thu
    0.38
    Ga
    0.37
    ofa
    0.37
    »;
    0.37
    Fortune
    0.37
    Activations Density 0.005%

    No Known Activations