© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174522
    Prev
    Next
    INDEX
    Explanations

    chemtrails

    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_20_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
     ફિલ્મ
    0.30
    忿
    0.28
    푞
    0.28
    ától
    0.28
     फिल्म
    0.26
    зора
    0.26
    film
    0.25
    𐰼
    0.25
     overwrite
    0.25
    很容易
    0.25
    POSITIVE LOGITS
     Bi
    0.25
     palabra
    0.25
     U
    0.24
     Comple
    0.23
    ENUM
    0.23
     haters
    0.23
     misi
    0.23
     étages
    0.23
     curves
    0.23
     missions
    0.22
    Activations Density 0.001%

    No Known Activations