© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81701
    Prev
    Next
    INDEX
    Explanations

    showing

    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_53_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
     Loose
    0.42
     loose
    0.38
    য়ান
    0.38
    ☒
    0.38
    らす
    0.38
     auß
    0.37
     evident
    0.37
    agée
    0.37
     लंबित
    0.36
     Lose
    0.36
    POSITIVE LOGITS
    াপতি
    0.41
    ਹੀਂ
    0.38
    Хо
    0.37
    Ho
    0.36
     Хо
    0.36
    egrad
    0.36
    தாவது
    0.36
    等的
    0.36
    
    0.35
     Мі
    0.35
    Activations Density 0.001%

    No Known Activations