© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 195914
    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_9_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
    \
    0.64
     you
    0.57
     trim
    0.52
     this
    0.48
     for
    0.48
     questo
    0.47
     sperm
    0.47
    0.47
     throm
    0.45
     Brum
    0.45
    POSITIVE LOGITS
    ം
    0.53
     спорта
    0.53
     कामगिरी
    0.53
    RationalValue
    0.52
     スト
    0.51
     ልዩ
    0.51
    addena
    0.51
    jourd
    0.50
     Ін
    0.50
    𒅴
    0.50
    Activations Density 0.000%

    No Known Activations