© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123112
    Prev
    Next
    INDEX
    Explanations

    electrical conductivity

    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_3_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
    电机
    0.58
     marqu
    0.57
    ig
    0.55
     främ
    0.54
    م
    0.54
     GV
    0.54
    uat
    0.53
     solicitud
    0.52
     важ
    0.52
     мотор
    0.52
    POSITIVE LOGITS
    )
    0.77
    0
    0.75
    ]
    0.67
     of
    0.66
    ى
    0.65
    ス
    0.65
    ے
    0.64
    л
    0.63
    ：
    0.62
     Colleges
    0.61
    Activations Density 0.001%

    No Known Activations