© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20689
    Prev
    Next
    INDEX
    Explanations

    *

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     bill
    0.70
    bill
    0.66
    빌
    0.50
     Bill
    0.49
    Bill
    0.48
     बिल
    0.46
     bills
    0.45
    bills
    0.44
     BILL
    0.42
     বিল
    0.41
    POSITIVE LOGITS
    Science
    0.58
     Science
    0.58
     science
    0.51
     W
    0.48
    science
    0.47
     наука
    0.46
     ciencia
    0.45
    SCIENCE
    0.44
    cience
    0.43
     Ciencia
    0.42
    Activations Density 0.020%

    No Known Activations