© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 234148
    Prev
    Next
    INDEX
    Explanations

    biodegradable

    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_32_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
     Collapse
    0.40
    ottie
    0.39
    collapse
    0.39
    コース
    0.38
    আত্ম
    0.38
    事項
    0.37
     раство
    0.37
     //{
    0.37
     சாய
    0.36
     Sour
    0.36
    POSITIVE LOGITS
     garden
    0.49
    garden
    0.46
     shifts
    0.45
     gardens
    0.44
     giardino
    0.43
     multif
    0.43
    multif
    0.43
     jardin
    0.42
     acuity
    0.41
    Garden
    0.40
    Activations Density 0.003%

    No Known Activations