© 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. 74482
    Prev
    Next
    INDEX
    Explanations

    eventually leading to an outcome

    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
     convergent
    0.36
     ביק
    0.33
     छुट
    0.32
     void
    0.31
     mt
    0.30
    ंद्र
    0.30
    ሟ
    0.30
    adic
    0.29
     instantaneous
    0.29
     nc
    0.29
    POSITIVE LOGITS
     Scienze
    0.34
     செ
    0.32
     Mauer
    0.30
    lishes
    0.29
     Frequent
    0.27
    unications
    0.27
    櫳
    0.27
    ங்கோ
    0.27
     Saber
    0.26
    未必
    0.26
    Activations Density 0.004%

    No Known Activations