© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 130434
    Prev
    Next
    INDEX
    Explanations

    mixed languages

    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
    øre
    0.42
    leys
    0.39
    Lem
    0.39
     النهايات
    0.38
     tecido
    0.37
    lemm
    0.37
     শে
    0.37
    샨
    0.37
    nuget
    0.35
    旖
    0.35
    POSITIVE LOGITS
     Sak
    0.45
     Al
    0.45
     al
    0.44
    Sak
    0.43
     SIL
    0.41
     susu
    0.41
    ixer
    0.41
     skl
    0.41
     дорого
    0.41
    সুর
    0.40
    Activations Density 0.002%

    No Known Activations