© 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. 200555
    Prev
    Next
    INDEX
    Explanations

    Thai

    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
     El
    0.57
     Mu
    0.51
     Eldorado
    0.47
    El
    0.45
     EL
    0.45
     X
    0.44
     B
    0.43
     Pat
    0.41
     mu
    0.41
     Patric
    0.41
    POSITIVE LOGITS
    Flo
    0.42
    ୩
    0.37
    lum
    0.37
    Th
    0.37
    Kaynak
    0.36
    dut
    0.36
    kode
    0.36
     flo
    0.36
    мах
    0.36
    dery
    0.36
    Activations Density 0.020%

    No Known Activations