© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 197660
    Prev
    Next
    INDEX
    Explanations

    tests and exams

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     based
    0.38
    syntax
    0.37
    setType
    0.37
    cej
    0.36
    based
    0.35
    Based
    0.35
    纯
    0.35
    para
    0.35
    classification
    0.35
    Som
    0.34
    POSITIVE LOGITS
     Answers
    0.62
    答案
    0.57
     answers
    0.56
     Answer
    0.53
     답
    0.50
    Answers
    0.50
     QUESTIONS
    0.50
     answer
    0.49
     Questions
    0.49
     questions
    0.47
    Activations Density 0.003%

    No Known Activations