© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36227
    Prev
    Next
    INDEX
    Explanations

    equate to / reducible to / semantic content

    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_11_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
    ون
    0.57
     ಇದರಿಂದ
    0.53
    ام
    0.53
    ق
    0.53
    ت
    0.52
    年
    0.52
    こんばんは
    0.50
    こんにちは
    0.50
    これにより
    0.50
    تح
    0.49
    POSITIVE LOGITS
     doby
    0.57
    வசம்
    0.54
     diarrhea
    0.53
     المقسوم
    0.51
    irá
    0.50
     ö
    0.49
    mites
    0.49
    롯
    0.49
    itudes
    0.48
     runny
    0.48
    Activations Density 0.028%

    No Known Activations