© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66032
    Prev
    Next
    INDEX
    Explanations

    Old Man

    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_41_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
     Old
    0.77
     old
    0.75
    Old
    0.70
     OLD
    0.62
     старо
    0.58
    old
    0.53
     vecchio
    0.53
    舊
    0.51
     olds
    0.50
    OLD
    0.49
    POSITIVE LOGITS
    धिकारियों
    0.42
    溲
    0.40
    דים
    0.38
    បង្
    0.37
    ডিয়াম
    0.37
     Nag
    0.36
    ണ്ടും
    0.36
    Crown
    0.35
     seiz
    0.35
     हड्ड
    0.35
    Activations Density 0.005%

    No Known Activations