© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215205
    Prev
    Next
    INDEX
    Explanations

    is a

    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_5_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
    t
    1.90
    د
    1.49
    क
    1.41
    ای
    1.34
    มี
    1.34
    দ
    1.26
    u
    1.25
    ז
    1.25
    สุ
    1.23
    م
    1.22
    POSITIVE LOGITS
    0
    1.46
     فى
    1.23
     يب
    1.22
     welke
    1.16
     ذكر
    1.16
     خاصة
    1.13
     تعريف
    1.13
     فِي
    1.13
     سين
    1.13
     první
    1.13
    Activations Density 0.000%

    No Known Activations