© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 154806
    Prev
    Next
    INDEX
    Explanations

    parts or sections

    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_50_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
    Die
    0.36
    تي
    0.35
     sắp
    0.35
     erő
    0.34
    rakech
    0.34
     interpersonal
    0.34
    ׂ
    0.33
    乚
    0.33
    ˦
    0.33
     surprise
    0.33
    POSITIVE LOGITS
     bagian
    1.45
     section
    1.41
     Section
    1.40
    Section
    1.38
    section
    1.30
     sections
    1.27
    部分
    1.26
     SECTION
    1.25
     القسم
    1.25
     portion
    1.24
    Activations Density 0.001%

    No Known Activations