© 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. 133913
    Prev
    Next
    INDEX
    Explanations

    locations and places

    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
    层次
    0.46
    eel
    0.40
     маъ
    0.38
    ël
    0.38
     ma
    0.38
     W
    0.37
     Hier
    0.37
     newMovie
    0.37
    lemm
    0.36
    हत
    0.36
    POSITIVE LOGITS
    itive
    0.45
    untes
    0.42
     الف
    0.38
     घन
    0.38
     मीणा
    0.37
    貳
    0.36
    ឧប
    0.36
     AVA
    0.35
    swith
    0.35
     ฟ
    0.35
    Activations Density 0.000%

    No Known Activations