© 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. 35923
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    និ
    0.40
    YW
    0.39
    inositol
    0.38
    푎
    0.38
     ASGI
    0.37
    wyn
    0.37
    mocks
    0.36
    ிறேன்
    0.36
    Assign
    0.36
    asarray
    0.36
    POSITIVE LOGITS
     Basement
    0.40
    ighe
    0.38
    ighet
    0.37
     basement
    0.37
     DET
    0.37
     棚
    0.37
    izu
    0.36
    ig
    0.36
    igt
    0.36
     LI
    0.36
    Activations Density 0.000%

    No Known Activations