© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63499
    Prev
    Next
    INDEX
    Explanations

    men

    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_46_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
    क्ष
    0.41
     Smok
    0.39
    শিষ্ট
    0.39
     marsh
    0.38
    áció
    0.38
    seb
    0.38
    ଶ
    0.37
    鲍
    0.36
     Baud
    0.36
     seb
    0.36
    POSITIVE LOGITS
     men
    1.23
     man
    1.07
    Men
    0.94
     Men
    0.93
    Man
    0.88
    men
    0.82
    男人
    0.82
     Man
    0.79
     uomini
    0.71
     الرجل
    0.71
    Activations Density 0.004%

    No Known Activations