© 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. 176380
    Prev
    Next
    INDEX
    Explanations

    gew/gw variations

    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
     STL
    0.44
    洨
    0.42
     PF
    0.42
     ট্র
    0.41
     recru
    0.41
    Tr
    0.41
    训
    0.40
     Tr
    0.40
     আল
    0.39
     அலெ
    0.39
    POSITIVE LOGITS
     gew
    1.03
    Gew
    1.01
     Gew
    0.97
    gew
    0.91
     gw
    0.77
     Gwen
    0.76
     GW
    0.74
    GW
    0.69
     Gw
    0.68
    Gw
    0.61
    Activations Density 0.001%

    No Known Activations