© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64807
    Prev
    Next
    INDEX
    Explanations

    attention, honor

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    輾
    0.41
    ’”
    0.40
    থে
    0.37
    kový
    0.37
    ويات
    0.36
     ষ্ট
    0.36
    აქ
    0.36
    จัก
    0.36
    ”:
    0.36
    sá
    0.36
    POSITIVE LOGITS
     sli
    0.38
     attentive
    0.38
     Bantu
    0.37
    Attention
    0.36
     VARI
    0.35
     Equatorial
    0.35
     attention
    0.35
     honorable
    0.35
     Honourable
    0.35
     puisi
    0.35
    Activations Density 0.002%

    No Known Activations