© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33080
    Prev
    Next
    INDEX
    Explanations

    mill / thousand

    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_50_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
     ter
    0.92
     TER
    0.91
     tere
    0.90
     터
    0.88
     Ter
    0.86
    Ter
    0.86
     Terry
    0.85
     Terra
    0.83
     티
    0.82
     Тер
    0.81
    POSITIVE LOGITS
     মিল
    0.53
     मिल
    0.45
     mill
    0.44
     Millar
    0.44
    amil
    0.43
     мили
    0.41
     milling
    0.40
    rola
    0.40
     milled
    0.39
    밀
    0.39
    Activations Density 0.096%

    No Known Activations