© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54731
    Prev
    Next
    INDEX
    Explanations

    b

    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_31_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
    ότητας
    0.26
    zid
    0.25
     formerly
    0.24
    Return
    0.24
    化
    0.24
     previously
    0.23
    rawal
    0.23
    first
    0.23
     prior
    0.23
    tmp
    0.23
    POSITIVE LOGITS
     różne
    0.26
     clopen
    0.26
     vaso
    0.25
     vasos
    0.25
    蕭
    0.24
     ceilings
    0.24
     moguć
    0.24
     compl
    0.24
     variés
    0.23
    getKeys
    0.23
    Activations Density 0.002%

    No Known Activations