© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 933
    Prev
    Next
    INDEX
    Explanations

    lookback

    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
    标
    0.26
     dispersal
    0.24
     GB
    0.23
     வழிபட்டால்
    0.23
     redire
    0.23
    킥
    0.22
     Ω
    0.22
     Durante
    0.22
     punto
    0.22
    얕
    0.22
    POSITIVE LOGITS
     سق
    0.25
     सोसाइटी
    0.24
    JQ
    0.23
    Acknowledgement
    0.23
    Context
    0.23
     context
    0.22
     jq
    0.22
    Recognition
    0.22
    ittle
    0.22
    adi
    0.22
    Activations Density 0.065%

    No Known Activations