© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 88752
    Prev
    Next
    INDEX
    Explanations

    taxi hailing service

    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_11_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
     pequeno
    0.25
     pequena
    0.24
     entrou
    0.24
     entered
    0.22
     neces
    0.22
     primeira
    0.22
     primeiro
    0.21
     ();
    0.21
     в
    0.20
     grise
    0.20
    POSITIVE LOGITS
    때
    0.26
    чені
    0.24
     해결
    0.22
    객
    0.22
     Ettha
    0.22
    solve
    0.22
    扪
    0.22
    leven
    0.21
    strdup
    0.21
    ckte
    0.21
    Activations Density 0.001%

    No Known Activations