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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30225
    Prev
    Next
    INDEX
    Explanations

    exams and banks

    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_40_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
     Conduct
    0.45
     Pants
    0.40
    斬
    0.38
     pants
    0.37
     Ceram
    0.37
     sult
    0.37
     lyn
    0.37
     Weil
    0.37
     Conducting
    0.37
     conduct
    0.36
    POSITIVE LOGITS
    influ
    0.49
    MediaStore
    0.40
    Influ
    0.39
    ウダー
    0.38
    觡
    0.37
    面试
    0.37
    occhi
    0.36
    Athena
    0.36
    Hindi
    0.36
    苍
    0.36
    Activations Density 0.001%

    No Known Activations