© 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. 196115
    Prev
    Next
    INDEX
    Explanations

    multilingual context

    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
    સ્તુ
    0.41
    রদ্ব
    0.41
     কই
    0.38
     Corporate
    0.37
     う
    0.36
     corporate
    0.36
    τουργ
    0.36
    द्धांत
    0.35
    itektur
    0.35
     ઉ
    0.35
    POSITIVE LOGITS
    獵
    0.44
     Nis
    0.42
     ני
    0.41
     parip
    0.41
     Nib
    0.41
     Гер
    0.39
     pril
    0.39
     prist
    0.38
     molyb
    0.38
     Prat
    0.38
    Activations Density 0.000%

    No Known Activations