© 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. 65078
    Prev
    Next
    INDEX
    Explanations

    find

    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
    cribing
    0.43
     Rug
    0.39
    loom
    0.36
     институт
    0.36
     पिक्च
    0.36
    intosh
    0.36
    设
    0.36
    藝
    0.36
     recorder
    0.36
    goo
    0.36
    POSITIVE LOGITS
     there
    0.43
     yourselves
    0.40
     harp
    0.39
    THERE
    0.39
     себя
    0.39
     वहाँ
    0.38
     होण्याची
    0.38
     Kati
    0.37
     તમારે
    0.36
     있다는
    0.36
    Activations Density 0.003%

    No Known Activations