© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 236335
    Prev
    Next
    INDEX
    Explanations

    surprise

    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_46_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
    orbit
    0.39
     ऑर्
    0.39
     القاعد
    0.38
     тә
    0.37
    言い
    0.37
    欹
    0.37
     ব্রিজ
    0.36
     திறன்
    0.36
    睜
    0.36
    createComponent
    0.36
    POSITIVE LOGITS
     sorpresa
    0.45
     Surprise
    0.44
     surprise
    0.42
     сю
    0.42
    표
    0.40
     ov
    0.38
    surprise
    0.38
     surpre
    0.38
    భి
    0.37
     surprises
    0.36
    Activations Density 0.003%

    No Known Activations