© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161871
    Prev
    Next
    INDEX
    Explanations

    основні, ефективні, конкретні, ключові

    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_31_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
    vé
    0.40
    ം
    0.36
    vés
    0.36
     হ্যা
    0.35
    Part
    0.35
    ads
    0.35
    ّم
    0.35
    グ
    0.35
    ég
    0.34
    í
    0.34
    POSITIVE LOGITS
    ಕರಣ
    0.38
    손
    0.38
     anticipating
    0.38
     بیوی
    0.38
    යින්
    0.38
    थिक
    0.38
     가지고
    0.37
    较
    0.37
     Mention
    0.37
    দায়িক
    0.37
    Activations Density 0.005%

    No Known Activations