© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164872
    Prev
    Next
    INDEX
    Explanations

    brown hair

    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_13_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
    🚃
    0.38
     İzmir
    0.35
     移動
    0.35
     releg
    0.34
     Türkei
    0.34
     izme
    0.33
    FileInputExcel
    0.33
    ீர்கள்
    0.33
     moisturizing
    0.33
    钠
    0.33
    POSITIVE LOGITS
     &
    0.40
    occhi
    0.37
    abili
    0.34
     வடி
    0.34
    ربعة
    0.34
    Am
    0.34
     Hardware
    0.33
     Accountants
    0.33
     Specialties
    0.33
    Á
    0.33
    Activations Density 0.001%

    No Known Activations