© 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. 134291
    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
     it
    1.00
     interpret
    0.92
     anál
    0.91
    มัน
    0.91
     triage
    0.89
     ř
    0.84
     r
    0.84
     can
    0.83
     solucion
    0.83
     nó
    0.82
    POSITIVE LOGITS
    с
    1.05
    modeling
    1.00
    s
    1.00
    <0x0D>
    0.98
    3
    0.98
    marked
    0.95
    mortem
    0.91
    natal
    0.90
    ,"
    0.90
    spanning
    0.90
    Activations Density 0.000%

    No Known Activations