© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 5637
    Prev
    Next
    INDEX
    Explanations

    here we

    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_38_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
    рию
    0.43
    mill
    0.37
    жность
    0.37
     качество
    0.36
     डीएस
    0.36
     Каждый
    0.36
    暇
    0.34
     структур
    0.34
     Рассмотрим
    0.34
    𝘵
    0.34
    POSITIVE LOGITS
    Curt
    0.48
    currentUser
    0.41
    KUR
    0.37
    comes
    0.37
     Curt
    0.37
     hart
    0.36
     याता
    0.36
     ruby
    0.35
     omitting
    0.35
    stimulating
    0.35
    Activations Density 0.137%

    No Known Activations