© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 206739
    Prev
    Next
    INDEX
    Explanations

    You are right to

    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_10_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
    0.61
    UnifiedTopology
    0.40
    liku
    0.40
    g
    0.38
    ภัย
    0.37
    Furniture
    0.35
     SPEAK
    0.35
    ların
    0.35
    ี่ยง
    0.34
    อาหาร
    0.34
    POSITIVE LOGITS
     for
    0.54
     لأ
    0.48
    ăți
    0.39
    for
    0.38
     e
    0.38
    and
    0.37
    ي
    0.37
     Latinoamérica
    0.35
    يلا
    0.35
     три
    0.34
    Activations Density 0.009%

    No Known Activations