© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 158064
    Prev
    Next
    INDEX
    Explanations

    web page styling

    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_50_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
    щихся
    0.37
    seyside
    0.36
    ких
    0.35
    案
    0.35
     Salerno
    0.33
     Deg
    0.33
    ских
    0.33
     handbook
    0.33
     Supra
    0.33
    ът
    0.32
    POSITIVE LOGITS
    渇
    0.43
    issements
    0.40
    ಸ್ಟ್
    0.37
    žia
    0.37
    LQ
    0.37
    uria
    0.36
    лта
    0.36
    ionista
    0.36
    urazione
    0.36
    indo
    0.36
    Activations Density 0.003%

    No Known Activations