© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216194
    Prev
    Next
    INDEX
    Explanations

    gambling, casinos, warranty, finance

    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
     SimSun
    0.41
    guns
    0.40
     ሥራ
    0.37
    rame
    0.36
    chu
    0.36
    荀
    0.36
    ುತ್ತಾರೆ
    0.36
    GridView
    0.35
    vação
    0.35
     Chinese
    0.35
    POSITIVE LOGITS
     иллюстра
    0.44
    illustrations
    0.41
     Warranty
    0.39
     иллюстрация
    0.39
     Overland
    0.39
    dokument
    0.39
    warranty
    0.38
     Warrant
    0.38
    ᴼ
    0.38
    лото
    0.37
    Activations Density 0.000%

    No Known Activations