© 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. 215007
    Prev
    Next
    INDEX
    Explanations

    produced by

    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
     ഹോ
    0.33
    Constant
    0.33
    constant
    0.33
    途
    0.33
    OUTPUT
    0.32
     constante
    0.31
     hallway
    0.31
     vector
    0.31
     خرج
    0.31
     ē
    0.30
    POSITIVE LOGITS
     prostitutes
    0.35
     GMO
    0.33
     CIA
    0.32
    羋
    0.31
     Pause
    0.31
     ಅಂಗ
    0.31
     synagogues
    0.30
     factories
    0.30
     Save
    0.30
     NRA
    0.30
    Activations Density 0.001%

    No Known Activations