© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31584
    Prev
    Next
    INDEX
    Explanations

    receipts

    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_50_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
    straction
    0.36
    epend
    0.35
    പോലെ
    0.35
     ബെ
    0.35
    
    0.35
    कला
    0.35
    瞬
    0.34
    髡
    0.34
     Uri
    0.34
    illerie
    0.34
    POSITIVE LOGITS
    receipt
    2.02
     receipt
    1.96
    Receipt
    1.94
     Receipt
    1.84
     receipts
    1.82
     Receipts
    1.70
     RECEIPTS
    1.48
     recib
    1.27
    RECE
    1.25
     RECE
    1.21
    Activations Density 0.004%

    No Known Activations