© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 137918
    Prev
    Next
    INDEX
    Explanations

    unusual characters

    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_46_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
     bellows
    0.38
     cinch
    0.38
     عادت
    0.38
    nang
    0.37
    rados
    0.36
     ወ
    0.36
     Kongo
    0.36
     os
    0.36
    Sel
    0.35
     Pos
    0.35
    POSITIVE LOGITS
     ফরজ
    0.41
    石
    0.39
    zca
    0.39
    zinc
    0.38
    istica
    0.38
    igne
    0.37
    વાહી
    0.37
    𝒟
    0.37
     نيك
    0.37
    akia
    0.37
    Activations Density 0.000%

    No Known Activations