© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100817
    Prev
    Next
    INDEX
    Explanations

    realized gains, losses, or transactions

    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_14_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
    च्च
    0.51
     Campania
    0.48
    渣
    0.47
     huéspedes
    0.47
    GRU
    0.46
     asiento
    0.46
     crude
    0.45
     siege
    0.45
     esp
    0.45
     FCM
    0.45
    POSITIVE LOGITS
    ','
    0.52
    ;.
    0.52
     Cig
    0.50
    +.
    0.50
     Shen
    0.49
     Receipts
    0.48
    říklad
    0.48
     Bedford
    0.47
    ële
    0.47
    ৃতির
    0.47
    Activations Density 0.012%

    No Known Activations