© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53626
    Prev
    Next
    INDEX
    Explanations

    Greek letters in quotes

    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_31_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
    ΤΟ
    0.40
     analysed
    0.36
    WHO
    0.36
     plantas
    0.36
    ̍
    0.36
     আস্থা
    0.35
    টে
    0.35
    板
    0.35
    τέ
    0.35
    植物
    0.35
    POSITIVE LOGITS
     drooping
    0.36
    geant
    0.36
    iosam
    0.36
     Shreveport
    0.36
     منف
    0.36
     возра
    0.35
     Sister
    0.35
    둑
    0.35
    lando
    0.35
     Seigneur
    0.35
    Activations Density 0.000%

    No Known Activations