© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 200099
    Prev
    Next
    INDEX
    Explanations

    NAACP

    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_37_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
     Lehr
    0.39
     energías
    0.39
    тні
    0.38
     syndrome
    0.38
     Syndrome
    0.38
     系
    0.38
     rationale
    0.37
    ᱶ
    0.37
    сных
    0.37
     சுவாச
    0.37
    POSITIVE LOGITS
     branch
    1.34
    branch
    1.14
     Branch
    1.06
    Branch
    1.05
     branches
    1.01
     BRANCH
    0.97
     cabang
    0.97
     ब्रांच
    0.96
    branches
    0.92
    支部
    0.92
    Activations Density 0.002%

    No Known Activations