© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210663
    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_20_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
     बोलते
    0.42
    撼
    0.42
     t
    0.41
    としても
    0.41
    publicKey
    0.39
    趨
    0.39
    取締
    0.39
     Carefully
    0.39
     τ
    0.38
    ThreadGroup
    0.37
    POSITIVE LOGITS
     سپور
    0.47
    otar
    0.45
    Akt
    0.44
    শাল
    0.44
    ेंसिल
    0.44
    dik
    0.43
     companhia
    0.43
     annotate
    0.43
    妏
    0.42
    সিডেন্ট
    0.42
    Activations Density 0.000%

    No Known Activations