© 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. 214119
    Prev
    Next
    INDEX
    Explanations

    eating

    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
    ሕ
    0.41
    दारा
    0.39
     ಶ
    0.38
    山田
    0.38
    似
    0.38
    ህ
    0.37
    纪
    0.37
    山の
    0.37
    క్య
    0.37
    шкина
    0.36
    POSITIVE LOGITS
     phag
    1.52
     Ph
    1.42
     fag
    1.42
    Ph
    1.38
     ph
    1.34
    ph
    1.34
     Fag
    1.31
     phage
    1.22
     фа
    1.20
    ophag
    1.03
    Activations Density 0.001%

    No Known Activations