© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 253589
    Prev
    Next
    INDEX
    Explanations

    Help

    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_56_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
    дже
    0.42
     re
    0.42
    ！】
    0.40
    ទុក
    0.38
     faceted
    0.38
    児
    0.37
     arcu
    0.36
    ］
    0.36
     সন্ধ্যায়
    0.36
    ндә
    0.36
    POSITIVE LOGITS
     Thanks
    0.55
    Thanks
    0.52
     thanks
    0.49
     Grazie
    0.49
     zahval
    0.47
     id
    0.47
     Dzięki
    0.47
     wanted
    0.46
     dank
    0.44
     grazie
    0.43
    Activations Density 0.001%

    No Known Activations