© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 121220
    Prev
    Next
    INDEX
    Explanations

    insurance, life, whole

    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_37_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
    arrerol
    0.33
     neutrophils
    0.31
     ബി
    0.31
     bromine
    0.31
     salicylate
    0.31
    ॕ
    0.30
    },\\
    0.30
     earths
    0.29
    ۾
    0.29
     midrange
    0.29
    POSITIVE LOGITS
    iagn
    0.33
     quite
    0.33
     really
    0.32
     couldn
    0.32
    ivores
    0.32
    pl
    0.31
    iles
    0.31
    í
    0.31
    oren
    0.31
    rv
    0.31
    Activations Density 0.024%

    No Known Activations