© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 251117
    Prev
    Next
    INDEX
    Explanations

    V

    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
     ψ
    0.42
    द्वानी
    0.40
     payoffs
    0.39
     tears
    0.35
     QP
    0.35
    ческому
    0.35
     X
    0.35
    Mq
    0.34
     pickups
    0.34
     osmosis
    0.34
    POSITIVE LOGITS
    train
    0.56
     Train
    0.53
     train
    0.51
     ट्रेन
    0.51
    Rail
    0.49
    火车
    0.49
     Trains
    0.47
    rail
    0.46
    Train
    0.46
     Rail
    0.45
    Activations Density 0.002%

    No Known Activations