© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202516
    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
    '
    1.41
    ק
    1.23
    ின்
    1.03
    า
    1.02
    ิ
    0.96
    ﻨ
    0.90
    ﺼ
    0.88
    ﺘ
    0.88
    ﻀ
    0.87
    も
    0.86
    POSITIVE LOGITS
     as
    1.54
     for
    1.26
     you
    1.25
     or
    1.23
     with
    1.06
     to
    1.03
     enkel
    1.03
     up
    1.01
     flights
    0.98
     and
    0.97
    Activations Density 0.000%

    No Known Activations