© 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. 235066
    Prev
    Next
    INDEX
    Explanations

    graphics

    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
    QAry
    0.40
     ajutor
    0.38
     DBHelper
    0.38
    提供的
    0.37
     tari
    0.37
     جي
    0.37
     vrijed
    0.37
    ঝ
    0.37
    Picker
    0.36
    جوم
    0.36
    POSITIVE LOGITS
     unleashing
    0.42
     డై
    0.37
     undertaken
    0.36
    ຊ
    0.35
    櫚
    0.34
     subjects
    0.34
     బల
    0.34
     Ot
    0.33
    eers
    0.33
    Scrim
    0.32
    Activations Density 0.000%

    No Known Activations