© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13267
    Prev
    Next
    INDEX
    Explanations

    database connection details

    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_15_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
    ifiably
    0.51
     contours
    0.49
     alerts
    0.46
    Microsoft
    0.46
    certified
    0.45
     wob
    0.45
     curves
    0.44
     reputations
    0.44
    ش
    0.43
     coefficients
    0.42
    POSITIVE LOGITS
    竹
    0.48
     রস
    0.46
     o
    0.46
    ait
    0.44
    水素
    0.44
    ecia
    0.43
     वहां
    0.43
    acid
    0.43
     자료
    0.43
     பொது
    0.42
    Activations Density 0.004%

    No Known Activations