© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201353
    Prev
    Next
    INDEX
    Explanations

    cancer research

    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
    Not in Any Lists

    No Comments

    Negative Logits
    㳊
    0.43
     Насе
    0.41
    тності
    0.39
     Сай
    0.38
     आनंद
    0.38
    朼
    0.37
    ंदी
    0.36
     ом
    0.36
    聝
    0.36
     叶
    0.36
    POSITIVE LOGITS
    癌
    0.64
     tumor
    0.57
     cancer
    0.53
     سرطان
    0.53
     doctors
    0.50
     cancers
    0.49
     scientists
    0.49
    醫
    0.49
     tumors
    0.48
    cancer
    0.47
    Activations Density 0.000%

    No Known Activations