© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196225
    Prev
    Next
    INDEX
    Explanations

    name 5 things you can

    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_27_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
     grated
    0.38
     гра
    0.35
     whipped
    0.35
    涙
    0.34
     markings
    0.33
     सांस
    0.32
     appBar
    0.32
     vibrations
    0.32
     జ్ఞాప
    0.32
     affixed
    0.31
    POSITIVE LOGITS
    الك
    0.39
    (";
    0.39
     কেনো
    0.37
     selfless
    0.37
     escolher
    0.36
    ujud
    0.36
    ந்துள்ளது
    0.36
     pretende
    0.35
    ზე
    0.35
    dinitro
    0.35
    Activations Density 0.002%

    No Known Activations