© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236861
    Prev
    Next
    INDEX
    Explanations

    questions about you or your specific situation

    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_25_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
    Displays
    0.40
     introdu
    0.39
     camels
    0.39
     tastings
    0.39
     حافظ
    0.38
     ჟ
    0.38
     apasion
    0.38
     trader
    0.37
     asta
    0.37
     Belling
    0.37
    POSITIVE LOGITS
     ค
    0.42
    ঞ্জে
    0.37
    gone
    0.36
     गर्नुहोस्
    0.34
    듭
    0.34
    𝗻
    0.34
     Worse
    0.34
     worse
    0.34
     WOR
    0.34
    Noise
    0.34
    Activations Density 0.001%

    No Known Activations