© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33558
    Prev
    Next
    INDEX
    Explanations

    algae blooms and marine life

    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_40_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
     Thermal
    0.51
     thermal
    0.46
     열
    0.41
     الحر
    0.41
     Urban
    0.41
     функций
    0.41
     CSO
    0.40
    Urban
    0.40
     сельского
    0.40
    thermal
    0.40
    POSITIVE LOGITS
    mosquito
    0.46
     fish
    0.44
    fish
    0.44
    鱼
    0.43
     fis
    0.43
     fishery
    0.42
    moderate
    0.41
    fisher
    0.41
    recursive
    0.40
    ɤ
    0.40
    Activations Density 0.035%

    No Known Activations