© 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. 16762
    Prev
    Next
    INDEX
    Explanations

    definite terms

    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
     reasonableness
    0.43
     unreasonable
    0.38
    బడి
    0.37
    埧
    0.36
     fault
    0.36
    Initially
    0.36
    饱和
    0.35
    含む
    0.34
     જાણી
    0.34
    ௭
    0.34
    POSITIVE LOGITS
     recite
    0.43
    祭
    0.43
     عنصر
    0.43
    Kang
    0.40
     functionals
    0.40
    estruct
    0.39
     উজ্জ
    0.39
    uper
    0.38
    esta
    0.38
     элемент
    0.38
    Activations Density 0.049%

    No Known Activations