© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37862
    Prev
    Next
    INDEX
    Explanations

    diversity, equity, inclusion

    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_3_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
    k
    0.86
    س
    0.70
    kz
    0.64
    g
    0.63
    الس
    0.63
    ຜະລິດຕ
    0.61
    cual
    0.60
    از
    0.60
    دة
    0.60
    तुरंग
    0.59
    POSITIVE LOGITS
     decentral
    0.67
    し
    0.66
    ット
    0.57
    ться
    0.57
    ()=>{
    0.57
     exercising
    0.55
    ї
    0.53
     appet
    0.53
    த்து
    0.52
     actuation
    0.52
    Activations Density 0.000%

    No Known Activations