© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15938
    Prev
    Next
    INDEX
    Explanations

    "constraints"

    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_34_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
     loadImage
    0.40
    ມາ
    0.39
    भाषा
    0.38
    ḡ
    0.38
    幕
    0.38
    갸
    0.38
    Attempts
    0.37
     evolución
    0.37
    ירת
    0.37
    כות
    0.36
    POSITIVE LOGITS
     ac
    0.44
    👋
    0.41
     serving
    0.41
     håll
    0.40
     अतिक
    0.40
    диви
    0.37
    ++++++++++++++++
    0.37
     एखाद्या
    0.36
    Serving
    0.36
     redeem
    0.36
    Activations Density 0.001%

    No Known Activations