© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 129693
    Prev
    Next
    INDEX
    Explanations

    starting points, basic knowledge, build rapport

    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_25_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
    厛
    0.46
    önes
    0.41
    ственная
    0.39
    বাধিকার
    0.38
    假期
    0.38
    म्प्ट
    0.38
    觛
    0.38
     सुनहरा
    0.37
     काले
    0.37
     tirar
    0.37
    POSITIVE LOGITS
     nuance
    0.45
     전략
    0.38
    muk
    0.38
     о
    0.37
     nuances
    0.37
    あた
    0.36
     systematic
    0.36
     Joni
    0.35
     methodology
    0.35
    дут
    0.35
    Activations Density 0.020%

    No Known Activations