© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207055
    Prev
    Next
    INDEX
    Explanations

    education and college

    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_20_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
    」
    0.42
    Ｗ
    0.39
     hoặc
    0.39
    または
    0.38
     achievement
    0.37
    stack
    0.37
     outcomes
    0.37
     نتائج
    0.37
    शीर
    0.37
     ع
    0.36
    POSITIVE LOGITS
     monsieur
    0.42
    титься
    0.40
    écie
    0.40
     tenis
    0.38
     étendue
    0.38
     spoke
    0.38
     Buddh
    0.38
     agress
    0.38
    乒
    0.37
     grise
    0.37
    Activations Density 0.001%

    No Known Activations