© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 134376
    Prev
    Next
    INDEX
    Explanations

    school related phrases

    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_1_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
    on
    1.46
    та
    1.34
    ut
    1.09
    It
    1.05
    You
    1.04
    ur
    1.02
    á
    0.95
    ou
    0.92
    ok
    0.92
    uk
    0.90
    POSITIVE LOGITS
    3
    0.87
     ব্যবস
    0.86
    ید
    0.86
    6
    0.79
    anych
    0.78
     welke
    0.78
     borderline
    0.77
     في
    0.75
     comple
    0.75
     ಸಾಮಾನ್ಯವಾಗಿ
    0.75
    Activations Density 0.001%

    No Known Activations