© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 69485
    Prev
    Next
    INDEX
    Explanations

    for

    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_51_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
     Super
    0.47
    super
    0.44
    Super
    0.44
    렌
    0.42
     ቅር
    0.39
     supercritical
    0.38
    elar
    0.38
    enumerate
    0.37
    enture
    0.37
     super
    0.36
    POSITIVE LOGITS
    Episodes
    0.43
    uellement
    0.42
    গ্রামী
    0.41
    ärer
    0.38
    iquement
    0.38
    izontal
    0.38
     ඔබ
    0.37
    хта
    0.37
    琤
    0.37
     آنچه
    0.37
    Activations Density 0.002%

    No Known Activations