© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 198694
    Prev
    Next
    INDEX
    Explanations

    gay people, card payment, 5 oz, the unicorn project, understanding the

    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
     jawab
    0.37
    ক্রম
    0.37
     graves
    0.36
     щ
    0.36
    гром
    0.35
    ﻒ
    0.35
    мед
    0.35
    кових
    0.34
     Cramer
    0.34
     jawaban
    0.34
    POSITIVE LOGITS
    Okay
    0.38
    البه
    0.37
    ವೆ
    0.35
    ിക്കുകയും
    0.35
    Improving
    0.35
     "}
    0.35
     সৌন্দর্য
    0.34
     Okay
    0.34
     озеро
    0.34
     kože
    0.33
    Activations Density 0.000%

    No Known Activations