© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6095
    Prev
    Next
    INDEX
    Explanations

    main ideas and topics

    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_39_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
     მი
    0.44
     লোকের
    0.37
    गोर
    0.37
     Май
    0.37
     Duval
    0.36
    䨘
    0.35
     இழ
    0.34
    folk
    0.34
    propTypes
    0.34
    姩
    0.34
    POSITIVE LOGITS
     ترکیه
    0.42
     trapezium
    0.39
    ថ្ងៃ
    0.39
     leukaemia
    0.38
     تاج
    0.37
     learnt
    0.37
    ceased
    0.36
     halved
    0.36
     idempot
    0.36
     watertight
    0.36
    Activations Density 0.001%

    No Known Activations