© 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. 30450
    Prev
    Next
    INDEX
    Explanations

    told someone something

    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
    vedad
    0.34
    illum
    0.32
    之一
    0.32
    nete
    0.31
     রক্ষার
    0.31
     EtOAc
    0.31
    ០
    0.31
     வெ
    0.30
    orso
    0.29
    hnen
    0.29
    POSITIVE LOGITS
     gist
    0.34
     nourished
    0.32
     regula
    0.32
     регули
    0.32
     Fed
    0.30
     provved
    0.30
     Subsect
    0.30
     তাহলে
    0.30
     роботу
    0.29
    rę
    0.29
    Activations Density 0.000%

    No Known Activations