© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 101578
    Prev
    Next
    INDEX
    Explanations

    Branches, road, wet

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    ন্ত্র
    0.43
    ∫
    0.40
     trataro
    0.39
     환경
    0.39
    bius
    0.39
    enação
    0.38
     XIV
    0.37
     ∫
    0.36
     жыл
    0.36
     Schroeder
    0.36
    POSITIVE LOGITS
     Branches
    0.44
     road
    0.40
     undefeated
    0.39
    Branches
    0.39
    Road
    0.39
    洖
    0.38
     wet
    0.36
    Wet
    0.35
    सु
    0.35
     ਸੁ
    0.35
    Activations Density 0.025%

    No Known Activations