© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2883
    Prev
    Next
    INDEX
    Explanations

    utilitarianism, utah, utterance, utanasana, ut

    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_39_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    boa
    0.38
    違い
    0.37
    カット
    0.37
     informe
    0.36
    بانی
    0.35
    禀
    0.34
    erful
    0.34
    ・・
    0.33
    muir
    0.33
    慣
    0.33
    POSITIVE LOGITS
     ut
    0.57
     UT
    0.52
    Ut
    0.50
     Ut
    0.48
     ут
    0.45
     justification
    0.43
    Utt
    0.42
     उत्
    0.40
     utter
    0.40
     justifications
    0.39
    Activations Density 0.038%

    No Known Activations