© 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. 233327
    Prev
    Next
    INDEX
    Explanations

    non

    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
     抗
    0.39
    zló
    0.39
     ब्र
    0.38
     GK
    0.38
     फिजिक्स
    0.37
    WithDictionary
    0.36
     jakie
    0.36
     Akademie
    0.36
     disadvantage
    0.35
    ঙ্ঘ
    0.35
    POSITIVE LOGITS
    ibilit
    0.42
     tịch
    0.40
    UpSync
    0.38
    instell
    0.38
    oguć
    0.38
     활
    0.37
     playful
    0.37
    ட்டில்
    0.37
    ewód
    0.37
    ervasyon
    0.37
    Activations Density 0.002%

    No Known Activations