© 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. 214055
    Prev
    Next
    INDEX
    Explanations

    quadruped

    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
    廟
    0.41
    untary
    0.41
    릴
    0.40
     BTU
    0.39
     MPG
    0.39
     Abbe
    0.39
     baza
    0.38
     webbrowser
    0.38
    риал
    0.38
    婆
    0.38
    POSITIVE LOGITS
    orn
    0.46
    hitting
    0.44
    alk
    0.40
     Ku
    0.40
     Cheers
    0.38
    äum
    0.38
    라운
    0.37
     Kath
    0.37
     मानने
    0.37
    欢
    0.37
    Activations Density 0.001%

    No Known Activations