© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 83751
    Prev
    Next
    INDEX
    Explanations

    religious groups or figures

    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_23_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
     Hamiltonian
    0.39
     LHS
    0.38
     」
    0.37
     cuy
    0.37
     RHS
    0.37
     accumulate
    0.36
    呐
    0.36
     CBS
    0.36
     chop
    0.36
     Thunderbird
    0.35
    POSITIVE LOGITS
     मुसलमानों
    0.42
     النساء
    0.42
    abled
    0.40
    urètre
    0.39
    bol
    0.38
     женщин
    0.38
     bullshit
    0.38
    itionen
    0.38
    pricing
    0.38
    嘘
    0.38
    Activations Density 0.001%

    No Known Activations