© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79140
    Prev
    Next
    INDEX
    Explanations

    models, learning, construction, table, Thai, writer

    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_31_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
    яд
    0.37
    ቦች
    0.37
    Semit
    0.36
     wholly
    0.35
     subscription
    0.34
    瞥
    0.34
     Buffered
    0.34
     golpe
    0.34
    ండ్లు
    0.34
    WW
    0.33
    POSITIVE LOGITS
     County
    0.37
     Community
    0.37
     کنم
    0.36
     Customer
    0.36
     знаю
    0.35
    лау
    0.35
    iterranée
    0.35
    늉
    0.35
    ple
    0.34
    áf
    0.34
    Activations Density 0.001%

    No Known Activations