© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64649
    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_46_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
    麻
    0.42
     المره
    0.41
    緍
    0.40
    uvre
    0.38
    ാലി
    0.38
    ผิด
    0.37
     contrary
    0.37
     نباش
    0.37
    春
    0.37
     Contrary
    0.36
    POSITIVE LOGITS
    tzmann
    0.44
     ENC
    0.41
    supp
    0.40
     BOM
    0.38
    Supp
    0.38
     管理
    0.38
    sciences
    0.38
    ぴ
    0.38
    QCD
    0.37
     Inventor
    0.37
    Activations Density 0.025%

    No Known Activations