© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129765
    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_6_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
    be
    1.36
    p
    1.32
    ro
    1.29
    ING
    1.09
    w
    1.09
    o
    1.07
    트
    1.06
    in
    1.02
    rin
    1.00
    Were
    1.00
    POSITIVE LOGITS
    ى
    1.03
    1.03
    0.99
    েল
    0.94
    ции
    0.93
     Ô
    0.93
    0.93
     It
    0.93
     seguir
    0.91
     linker
    0.91
    Activations Density 0.000%

    No Known Activations