© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 139018
    Prev
    Next
    INDEX
    Explanations

    three

    np_max-act-logits · gemini-2.5-flash-lite
    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
     چهار
    0.47
    四
    0.47
     चौथ
    0.46
     四
    0.46
     Pedro
    0.43
     চারটি
    0.43
     vier
    0.42
    四个
    0.42
     Gad
    0.42
     पदा
    0.41
    POSITIVE LOGITS
    Three
    0.55
     Three
    0.53
     üç
    0.53
     THREE
    0.52
    三
    0.50
     трех
    0.49
    THREE
    0.49
     three
    0.48
     Drei
    0.46
     trei
    0.46
    Activations Density 0.017%

    No Known Activations