© 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. 28931
    Prev
    Next
    INDEX
    Explanations

    career changers, explorations, switch

    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
    দাতা
    0.44
    Plan
    0.43
    Japanese
    0.36
    日本人
    0.36
     Plan
    0.35
    乃
    0.35
    규모
    0.35
    ouch
    0.34
     مخصوص
    0.34
    Olymp
    0.34
    POSITIVE LOGITS
     Vell
    0.39
     glob
    0.38
     History
    0.38
    foss
    0.38
     vect
    0.38
    停
    0.38
     progressive
    0.37
     Foo
    0.37
     curvil
    0.37
     Sia
    0.37
    Activations Density 0.004%

    No Known Activations