© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37096
    Prev
    Next
    INDEX
    Explanations

    significant findings or updates

    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_11_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
     r
    0.75
    :*
    0.70
    ↵
    0.70
     [
    0.68
    :
    0.65
     i
    0.64
    2
    0.64
     :
    0.62
     (
    0.61
     wineries
    0.61
    POSITIVE LOGITS
     millón
    0.58
     toneladas
    0.58
     sobre
    0.54
    દો
    0.54
    halle
    0.54
    🆁
    0.51
     erwähnt
    0.51
    hala
    0.51
    িল্ল
    0.50
    Sobre
    0.50
    Activations Density 0.040%

    No Known Activations