© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 206069
    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_10_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
    ,
    0.46
    taking
    0.43
     wading
    0.43
    imerick
    0.41
    Depending
    0.39
     unconventional
    0.38
    姩
    0.38
    Something
    0.38
    MP
    0.37
    usiasm
    0.37
    POSITIVE LOGITS
    ٹ
    0.60
     eje
    0.54
    ्वेस्ट
    0.53
     sám
    0.53
    Salle
    0.52
     erz
    0.52
    𒁀
    0.52
     använd
    0.51
    vée
    0.51
    müş
    0.51
    Activations Density 0.000%

    No Known Activations