© 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. 85148
    Prev
    Next
    INDEX
    Explanations

    protective gear

    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
    Від
    0.55
    ні
    0.50
    Questo
    0.50
     lakini
    0.49
    넬
    0.48
    Esta
    0.47
    цію
    0.47
     miglior
    0.47
    Лі
    0.47
    Denne
    0.46
    POSITIVE LOGITS
     $\
    0.48
    geq
    0.48
     cold
    0.45
    orec
    0.45
     pt
    0.43
     hor
    0.43
    ">
    0.41
     endocrine
    0.41
    ':
    0.41
     elderly
    0.41
    Activations Density 0.001%

    No Known Activations