© 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. 127679
    Prev
    Next
    INDEX
    Explanations

    endanger children

    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
    डो
    0.40
    armen
    0.37
    }};
    0.37
    Glor
    0.36
    აძ
    0.35
    贲
    0.35
    ഭവ
    0.34
     orice
    0.34
    ذف
    0.34
     }];
    0.34
    POSITIVE LOGITS
     кола
    0.47
     nonlinearity
    0.45
     Insulation
    0.37
     plaques
    0.36
     dementia
    0.36
     stray
    0.36
     Frobenius
    0.35
     Alzheimer
    0.35
    ನೀ
    0.35
    ἂ
    0.35
    Activations Density 0.005%

    No Known Activations