© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118330
    Prev
    Next
    INDEX
    Explanations

    uncensored

    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_27_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
     Soils
    0.27
     Geology
    0.26
     contemporaneous
    0.26
     этот
    0.26
     Этот
    0.25
     Received
    0.25
    旨
    0.25
    勍
    0.25
    㑯
    0.25
     consecutive
    0.25
    POSITIVE LOGITS
    ufthansa
    0.27
    balancer
    0.25
    Yard
    0.25
     allerg
    0.24
    allerg
    0.24
    ün
    0.23
    dropdown
    0.23
    april
    0.23
    Mum
    0.23
     antihist
    0.23
    Activations Density 0.006%

    No Known Activations