© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 207212
    Prev
    Next
    INDEX
    Explanations

    Mercedes

    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_56_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
    ക്ഷി
    0.37
     ben
    0.37
     фи
    0.37
    ("&
    0.36
     -"
    0.36
    സ്ട
    0.36
     மட
    0.36
    Sierra
    0.35
    渑
    0.34
     -(
    0.34
    POSITIVE LOGITS
    Bad
    0.54
     Bad
    0.43
     percorso
    0.43
     bad
    0.42
    bad
    0.42
    divisions
    0.40
    坏
    0.40
     benefited
    0.39
     противопо
    0.39
     division
    0.38
    Activations Density 0.000%

    No Known Activations