© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 655
    Prev
    Next
    INDEX
    Explanations

    Nature, water, animals, peat, caves, insurance

    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_40_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
    ஜ்மஹால்
    0.38
    艶
    0.38
     devast
    0.37
     chl
    0.37
     devastating
    0.36
    Dam
    0.35
     सड़क
    0.35
    今は
    0.35
    ...)
    0.34
     canals
    0.34
    POSITIVE LOGITS
    法施行
    0.38
     Alvarez
    0.36
    归
    0.36
    ToList
    0.35
     Seventh
    0.35
    ಗೊಂಡ
    0.35
     RTC
    0.34
     seventy
    0.34
    alang
    0.34
    SPC
    0.34
    Activations Density 0.015%

    No Known Activations