© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62120
    Prev
    Next
    INDEX
    Explanations

    où followed by French phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_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
    لما
    0.64
    ने
    0.63
    на
    0.60
    gum
    0.59
     リー
    0.58
    पुरा
    0.57
     ८
    0.57
    الث
    0.57
    smöglichkeiten
    0.55
    a
    0.55
    POSITIVE LOGITS
     BAI
    0.53
     Collins
    0.49
     WEST
    0.49
     Ozzy
    0.48
     Halo
    0.48
     পারছি
    0.48
    <0x93>
    0.47
     Overwatch
    0.47
     TEA
    0.47
     MAD
    0.46
    Activations Density 0.000%

    No Known Activations