© 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. 179036
    Prev
    Next
    INDEX
    Explanations

    multilingual phrases

    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
     ث
    0.73
     الث
    0.71
    الث
    0.64
     Th
    0.58
     thump
    0.58
     th
    0.57
     थ
    0.56
    Th
    0.56
    Hu
    0.53
     Hu
    0.51
    POSITIVE LOGITS
    Charsets
    0.41
    Sunset
    0.40
    vital
    0.40
     Vital
    0.39
     duty
    0.38
    سر
    0.38
    㳓
    0.38
    Vital
    0.37
    泷
    0.37
     ras
    0.36
    Activations Density 0.001%

    No Known Activations