© 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. 6517
    Prev
    Next
    INDEX
    Explanations

    Error: messages

    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
     اعت
    0.45
    ၇
    0.39
     ringan
    0.38
     thiệt
    0.38
    upid
    0.36
    dni
    0.36
     cộng
    0.36
    뿔
    0.36
     Serialize
    0.36
     гидро
    0.36
    POSITIVE LOGITS
     சத
    0.40
     estimators
    0.38
     Stat
    0.38
     editorials
    0.36
     "**
    0.36
     Rag
    0.35
    つき
    0.35
    Unable
    0.35
     collectors
    0.35
     shan
    0.35
    Activations Density 0.022%

    No Known Activations