© 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. 26711
    Prev
    Next
    INDEX
    Explanations

    file paths

    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
     public
    2.00
    public
    1.88
    Public
    1.66
     Public
    1.61
     PUBLIC
    1.58
    PUBLIC
    1.55
     सार्वजनिक
    1.52
     публи
    1.50
    公
    1.45
     öffentlichen
    1.38
    POSITIVE LOGITS
    延
    0.41
    อป
    0.35
     ble
    0.33
     Gig
    0.33
    cmb
    0.33
     barring
    0.33
     ምን
    0.33
    题材
    0.33
    벳
    0.33
     মহাপ
    0.33
    Activations Density 0.014%

    No Known Activations