© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137612
    Prev
    Next
    INDEX
    Explanations

    Tibetan and Buddhist terms

    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_12_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
     op
    0.51
     .
    0.50
     Q
    0.48
     bronze
    0.47
     sapphire
    0.47
    ]
    0.47
     BH
    0.46
     Visa
    0.46
     opal
    0.45
     "
    0.45
    POSITIVE LOGITS
    ERV
    0.58
    ários
    0.54
    cké
    0.54
    ЕР
    0.53
    ANTES
    0.51
    être
    0.50
    服务
    0.50
    ÕES
    0.50
     ಎಸ್
    0.50
    Ｔ
    0.50
    Activations Density 0.000%

    No Known Activations