© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33383
    Prev
    Next
    INDEX
    Explanations

    Wang/King

    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
     NAN
    0.62
     Nan
    0.61
    Dong
    0.59
     Dong
    0.59
    东
    0.58
     dong
    0.56
    Nan
    0.55
     N
    0.53
     nanotechnology
    0.53
    東
    0.53
    POSITIVE LOGITS
    王
    0.57
     Wang
    0.51
     wang
    0.51
    Wang
    0.49
     왕
    0.45
    wang
    0.44
    rlig
    0.43
    왕
    0.42
    My
    0.41
     Vương
    0.40
    Activations Density 0.004%

    No Known Activations