© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 2015
    Prev
    Next
    INDEX
    Explanations

    real estate development and sales

    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_38_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
    orbidity
    0.42
    Leffler
    0.39
    ฬ
    0.39
     radiolysis
    0.38
     गिरि
    0.38
     Thurman
    0.37
    rophic
    0.36
    {&
    0.36
    adecimal
    0.35
    нти
    0.35
    POSITIVE LOGITS
     condo
    0.79
     apartment
    0.68
     sales
    0.64
     condominium
    0.64
     condos
    0.63
     developer
    0.63
    developer
    0.63
     Sales
    0.61
    Developer
    0.61
     Developer
    0.61
    Activations Density 0.052%

    No Known Activations