© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 235820
    Prev
    Next
    INDEX
    Explanations

    case study

    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_25_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
     l
    0.43
     th
    0.42
     van
    0.42
     de
    0.40
     fellows
    0.38
     saw
    0.38
    rat
    0.38
     Lam
    0.38
     c
    0.38
     with
    0.37
    POSITIVE LOGITS
     (#{
    0.50
    UseDebug
    0.48
    𝕦
    0.46
    вости
    0.46
    ανο
    0.45
     muque
    0.44
    परेटर
    0.43
    ன்ஹீ
    0.43
    起始
    0.43
    ब्दिक
    0.43
    Activations Density 0.000%

    No Known Activations