© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 158169
    Prev
    Next
    INDEX
    Explanations

    military academy

    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
    ล็
    0.40
    лето
    0.39
    addena
    0.39
     pinMode
    0.38
     Locking
    0.38
     planis
    0.38
    ред
    0.37
    ठ
    0.37
    銑
    0.37
    ্ল
    0.36
    POSITIVE LOGITS
    ans
    0.40
    akers
    0.37
     incont
    0.37
    Squ
    0.36
    বিল
    0.36
    ocalization
    0.36
    answ
    0.36
    Kan
    0.36
    acker
    0.36
     Gul
    0.36
    Activations Density 0.000%

    No Known Activations