© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33728
    Prev
    Next
    INDEX
    Explanations

    asked permission, let us, let me

    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_40_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
     persuade
    0.45
     convinc
    0.44
     persuas
    0.42
     persuaded
    0.41
     persuasive
    0.41
     persuading
    0.40
    aurant
    0.40
    食堂
    0.38
     convince
    0.38
    瞍
    0.38
    POSITIVE LOGITS
     configurational
    0.40
     voting
    0.40
    utilisation
    0.38
     authorise
    0.37
     Конститу
    0.36
     প্রতিনিধি
    0.36
     authorisation
    0.36
     Cornish
    0.36
     fat
    0.35
    personal
    0.35
    Activations Density 0.000%

    No Known Activations